© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40518
    Prev
    Next
    INDEX
    Explanations

    organizations and legislative information

    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
    447
    +0.33
    1.9%
    393
    +0.21
    1.2%
    739
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.33
    0.31
    484
    +0.21
    0.17
    384
    +0.09
    0.10
    Negative Logits
    :(
    -0.59
    elle
    -0.56
     horm
    -0.53
     Reporter
    -0.52
    ieg
    -0.52
    minist
    -0.51
    itate
    -0.51
    physical
    -0.49
    ital
    -0.49
    hemer
    -0.48
    POSITIVE LOGITS
     vice
    0.68
     other
    0.58
     thence
    0.57
     assorted
    0.56
     Associates
    0.56
     onwards
    0.55
     Orange
    0.55
     thus
    0.55
     consequently
    0.53
    MSN
    0.53
    Activations Density 12.677%

    No Known Activations