© 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. 10
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical details, particularly related to algorithms or programming

    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
    575
    +0.14
    0.6%
    187
    +0.13
    0.5%
    113
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    63
    +0.14
    0.03
    230
    +0.13
    0.03
    538
    +0.11
    0.02
    Negative Logits
    riot
    -0.86
    âĸ¬âĸ¬
    -0.83
    riots
    -0.82
    inant
    -0.78
    quez
    -0.75
    ruciating
    -0.75
    Ò
    -0.74
    ophobic
    -0.72
    hua
    -0.72
    ãĥ¯ãĥ³
    -0.72
    POSITIVE LOGITS
    kson
    0.94
    arov
    0.76
    uably
    0.72
    edo
    0.71
     Occupations
    0.70
    bes
    0.70
     Waste
    0.69
    led
    0.69
    ei
    0.68
     Cheong
    0.67
    Activations Density 0.089%

    No Known Activations