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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2612
    Prev
    Next
    INDEX
    Explanations

    statistical analysis terms and quantitative measurement values in scientific texts

    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
    459
    +0.12
    0.5%
    649
    +0.12
    0.4%
    445
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.12
    0.03
    699
    +0.12
    0.02
    328
    +0.12
    0.02
    Negative Logits
    loo
    -0.98
    ASED
    -0.97
     accomp
    -0.97
    ajo
    -0.95
     helicop
    -0.93
    into
    -0.92
     facult
    -0.91
    hani
    -0.90
     tremend
    -0.88
    DOM
    -0.88
    POSITIVE LOGITS
     spirited
    0.97
    erest
    0.85
    iors
    0.84
    ered
    0.82
    ering
    0.81
     Nashville
    0.80
     Gates
    0.78
    ities
    0.77
    izens
    0.76
    esm
    0.75
    Activations Density 0.312%

    No Known Activations