© 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. 37209
    Prev
    Next
    INDEX
    Explanations

    descriptions of past events or situations with emphasis on specific numbers or quantities

    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
    223
    +0.08
    0.5%
    653
    +0.08
    0.5%
    153
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    344
    +0.08
    0.12
    223
    +0.08
    0.10
    366
    +0.08
    0.08
    Negative Logits
    grave
    -0.65
    yrinth
    -0.60
    pattern
    -0.58
    impl
    -0.52
    ment
    -0.50
    acus
    -0.49
    comb
    -0.48
    orthodox
    -0.47
     destro
    -0.47
     sacrific
    -0.47
    POSITIVE LOGITS
     cents
    0.75
     weeks
    0.74
    teenth
    0.74
     minutes
    0.70
     hours
    0.69
     clicks
    0.68
     inches
    0.65
     days
    0.62
     seconds
    0.60
     hundred
    0.60
    Activations Density 7.205%

    No Known Activations