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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 14048
    Prev
    Next
    INDEX
    Explanations

    file names or technical specifications

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    640
    +0.22
    1.0%
    393
    +0.19
    0.8%
    756
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.22
    0.04
    640
    +0.19
    0.03
    64
    +0.14
    -0.01
    Negative Logits
     veter
    -0.87
    lies
    -0.84
     advoc
    -0.79
     quir
    -0.78
     perspect
    -0.74
     mathemat
    -0.72
     pse
    -0.70
     tremend
    -0.70
    ptive
    -0.68
     policymakers
    -0.68
    POSITIVE LOGITS
     Otherwise
    0.99
     Later
    0.98
     Secondly
    0.94
     Lastly
    0.93
     Afterwards
    0.93
     Alternatively
    0.92
    done
    0.91
     Likewise
    0.91
     Converted
    0.91
     Anyway
    0.89
    Activations Density 0.057%

    No Known Activations