© 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. 1197
    Prev
    Next
    INDEX
    Explanations

    statistical and mathematical terms, with a focus on regression analysis and scientific procedures

    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
    640
    +0.14
    0.5%
    603
    +0.12
    0.5%
    341
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.14
    0.02
    699
    +0.12
    0.03
    603
    +0.12
    0.04
    Negative Logits
    SPONSORED
    -1.14
    soDeliveryDate
    -1.08
    wcs
    -1.00
    lations
    -0.97
    thinkable
    -0.93
    rity
    -0.93
    matic
    -0.90
    sonian
    -0.86
    erk
    -0.85
    bial
    -0.85
    POSITIVE LOGITS
    ============
    1.26
    ========
    1.25
    ===
    0.88
     sidx
    0.86
     variance
    0.83
    -+-+-+-+
    0.79
     mos
    0.75
     304
    0.75
     rall
    0.74
     envy
    0.73
    Activations Density 0.393%

    No Known Activations