© 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. 5492
    Prev
    Next
    INDEX
    Explanations

    mentions of unnamed or unspecified individuals or entities

    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
    679
    +0.18
    0.6%
    469
    +0.14
    0.5%
    132
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.18
    0.06
    132
    +0.14
    0.07
    625
    +0.14
    0.06
    Negative Logits
     Herald
    -0.88
    ctor
    -0.84
    Url
    -0.83
     Hulk
    -0.81
     Consent
    -0.81
     Parenthood
    -0.79
    ihara
    -0.78
     centerpiece
    -0.78
    Accessory
    -0.78
     Rape
    -0.77
    POSITIVE LOGITS
    paces
    1.17
    hots
    1.12
    ystem
    1.03
     who
    1.00
    cript
    0.98
    heastern
    0.98
    cius
    0.97
    poons
    0.95
     intercepted
    0.95
    hips
    0.94
    Activations Density 1.715%

    No Known Activations