© 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. 31129
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal sentiments and motivations

    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
    +0.26
    1.2%
    393
    +0.13
    0.6%
    566
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.26
    0.32
    447
    +0.13
    0.34
    64
    +0.11
    -0.17
    Negative Logits
     Annotations
    -0.57
    hips
    -0.53
    animal
    -0.53
     NX
    -0.52
     apex
    -0.51
     Dayton
    -0.50
     treatments
    -0.50
     excess
    -0.50
     TER
    -0.49
     -----
    -0.48
    POSITIVE LOGITS
    zbollah
    1.14
    unes
    1.06
    self
    1.00
    iner
    0.91
    anyahu
    0.87
    achi
    0.87
    asca
    0.85
    anium
    0.84
    chwitz
    0.83
    amins
    0.83
    Activations Density 9.431%

    No Known Activations