© 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. 14032
    Prev
    Next
    INDEX
    Explanations

    discussion points or questions regarding specific topics in a given context

    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
    393
    +0.17
    0.5%
    708
    +0.15
    0.5%
    353
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    236
    +0.17
    0.07
    708
    +0.15
    0.05
    353
    +0.14
    0.05
    Negative Logits
    enos
    -1.02
    ãĥ¼ãĤ¯
    -0.98
    roid
    -0.96
    ashes
    -0.93
    ãĤª
    -0.93
    ourcing
    -0.93
    rosse
    -0.93
     Syndrome
    -0.92
     Deity
    -0.91
     VIDEOS
    -0.91
    POSITIVE LOGITS
    yip
    1.15
    iably
    1.14
    fy
    1.12
    tar
    1.12
    llor
    1.11
     you
    1.06
     preferably
    1.01
     anything
    0.99
    uana
    0.96
     they
    0.95
    Activations Density 0.453%

    No Known Activations