© 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. 5288
    Prev
    Next
    INDEX
    Explanations

    detailed information about flights, passengers, and incidents related to travel

    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
    611
    +0.14
    0.5%
    393
    +0.14
    0.5%
    549
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.07
    608
    +0.14
    0.08
    669
    +0.14
    0.07
    Negative Logits
    vic
    -1.08
    TEXT
    -1.06
    jury
    -1.05
    scientific
    -1.05
    few
    -0.95
    mask
    -0.94
    stros
    -0.92
    faced
    -0.92
    inth
    -0.92
    wolves
    -0.91
    POSITIVE LOGITS
     thence
    1.47
     afar
    1.43
     whence
    1.32
     abroad
    1.18
     Poland
    0.96
     across
    0.95
     atop
    0.94
    udeb
    0.94
     within
    0.92
     somewhere
    0.91
    Activations Density 0.835%

    No Known Activations