© 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. 45655
    Prev
    Next
    INDEX
    Explanations

    code snippets related to programming languages and processes

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    48
    +0.13
    0.7%
    132
    +0.09
    0.5%
    359
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    68
    +0.13
    0.08
    107
    +0.09
    0.07
    48
    +0.08
    0.10
    Negative Logits
    idge
    -0.56
     Lauder
    -0.56
     Ramsay
    -0.55
     shove
    -0.55
     coast
    -0.54
    İĭ
    -0.54
     Ches
    -0.53
     Winchester
    -0.53
     pole
    -0.52
     Vale
    -0.51
    POSITIVE LOGITS
    !--
    1.06
    ullah
    0.76
    sup
    0.70
    ...]
    0.69
    âĢ¦]
    0.68
    erences
    0.67
    img
    0.66
    div
    0.66
    span
    0.65
    bean
    0.64
    Activations Density 6.026%

    No Known Activations