© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE E2E Recon
    5. 6-RES_SCEFR-AJT
    6. 3668
    Prev
    Next
    INDEX
    Explanations

    mentions related to legal or criminal investigations, contents about medical treatments and descriptions of physical harm or injury

    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
    10
    +0.11
    0.5%
    288
    +0.11
    0.5%
    202
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.21
    575
    +0.11
    0.16
    762
    +0.11
    0.17
    Negative Logits
    eor
    -0.83
    ulic
    -0.80
    inder
    -0.79
    xtap
    -0.78
    ao
    -0.77
    adj
    -0.74
    irt
    -0.74
    lav
    -0.73
    ools
    -0.72
    odd
    -0.71
    POSITIVE LOGITS
     behavi
    0.96
     regarding
    0.90
     respecting
    0.88
     wrongdoing
    0.86
     ALS
    0.85
     whistleblowers
    0.83
    !!!!!
    0.82
     concerning
    0.82
     :(
    0.82
    emort
    0.81
    Activations Density 4.816%

    No Known Activations