© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1549
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms, including names of individuals, organizations, and locations

    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
    137
    +0.16
    0.5%
    128
    +0.16
    0.5%
    211
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.16
    0.06
    211
    +0.16
    0.03
    376
    +0.16
    0.04
    Negative Logits
     Occupations
    -1.23
    HER
    -1.07
    UAL
    -1.04
    gerald
    -1.03
    uality
    -1.02
    LER
    -0.97
    ullah
    -0.93
    Condition
    -0.93
    mble
    -0.92
    enegger
    -0.91
    POSITIVE LOGITS
    anche
    1.74
    itzer
    1.73
    asts
    1.51
    anco
    1.50
    anca
    1.47
    adders
    1.43
    anches
    1.42
    ossom
    1.40
    adder
    1.40
    asted
    1.38
    Activations Density 1.440%

    No Known Activations