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

    Neuronpedia

    Jacobian LensNEW
    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. 33367
    Prev
    Next
    INDEX
    Explanations

    instances where actions or decisions are taken in place of other actions or decisions

    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
    +0.39
    2.2%
    669
    +0.12
    0.7%
    94
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.39
    0.31
    608
    +0.12
    0.22
    14
    +0.10
    0.07
    Negative Logits
    artisan
    -0.56
    Nap
    -0.54
    read
    -0.54
    Vers
    -0.54
     Palestin
    -0.53
    marine
    -0.51
    anded
    -0.50
    essen
    -0.50
    Guest
    -0.49
    STAT
    -0.49
    POSITIVE LOGITS
     quitting
    0.56
     rever
    0.56
     being
    0.55
     fixing
    0.53
     dwelling
    0.53
     wasting
    0.53
     clock
    0.53
     retiring
    0.52
     anger
    0.52
     anything
    0.52
    Activations Density 13.812%

    No Known Activations