© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 31317
    Prev
    Next
    INDEX
    Explanations

    texts related to exploration of concepts or activities that help one improve oneself or understand the world around them, such as meditation, self-improvement, awareness, or handling challenges

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.24
    1.2%
    402
    +0.11
    0.5%
    483
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    483
    +0.24
    0.11
    616
    +0.11
    0.12
    402
    +0.11
    0.10
    Negative Logits
    onto
    -0.64
    onite
    -0.60
     tolerated
    -0.59
    orest
    -0.59
    heed
    -0.58
    ourge
    -0.57
    itiz
    -0.57
     intimately
    -0.57
    ctrl
    -0.56
     unemploy
    -0.56
    POSITIVE LOGITS
     nutshell
    0.86
     meantime
    0.86
     case
    0.86
     cases
    0.86
     context
    0.83
     guise
    0.74
     vein
    0.70
     absence
    0.69
     embodiments
    0.68
    lance
    0.67
    Activations Density 12.158%

    No Known Activations