© 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. 14308
    Prev
    Next
    INDEX
    Explanations

    words related to genealogy and ancestry

    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
    549
    +0.12
    0.6%
    441
    +0.10
    0.5%
    183
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.12
    0.11
    352
    +0.10
    0.10
    23
    +0.08
    0.10
    Negative Logits
    isites
    -0.64
    idge
    -0.61
    icum
    -0.61
    isc
    -0.61
    eem
    -0.58
     Jelly
    -0.56
     Despair
    -0.56
    isson
    -0.55
    izen
    -0.55
    idence
    -0.55
    POSITIVE LOGITS
    cest
    0.87
    ral
    0.80
    alog
    0.75
    bour
    0.71
    rals
    0.66
    alogy
    0.66
    liest
    0.63
    rings
    0.58
    rir
    0.58
    bors
    0.56
    Activations Density 0.757%

    No Known Activations