© 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. 10974
    Prev
    Next
    INDEX
    Explanations

    details related to specifications, dimensions, and materials

    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
    172
    +0.11
    0.6%
    84
    +0.10
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.07
    232
    +0.10
    0.04
    343
    +0.10
    0.04
    Negative Logits
    ardless
    -0.73
    âķIJâķIJ
    -0.63
    theless
    -0.60
     fertility
    -0.59
    spring
    -0.57
    arding
    -0.57
     incub
    -0.57
    ounge
    -0.57
    ONG
    -0.56
     fertil
    -0.56
    POSITIVE LOGITS
    emia
    0.77
    elines
    0.77
    adr
    0.72
    eteria
    0.67
    arus
    0.67
    acio
    0.66
     Fas
    0.65
    urus
    0.65
    ay
    0.64
    eworks
    0.63
    Activations Density 0.421%

    No Known Activations