© 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 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. 7091
    Prev
    Next
    INDEX
    Explanations

    time-related terms like months, years, and weeks

    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
    651
    +0.19
    0.6%
    71
    +0.19
    0.6%
    718
    +0.17
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.19
    0.07
    279
    +0.19
    0.06
    132
    +0.17
    0.05
    Negative Logits
    tymology
    -1.22
    ega
    -1.15
    drawn
    -1.03
    dinand
    -1.00
    anamo
    -1.00
    emort
    -0.99
    agra
    -0.99
    ye
    -0.98
    MpServer
    -0.98
    lua
    -0.98
    POSITIVE LOGITS
     thereafter
    1.55
    night
    1.03
     basis
    1.02
     cycle
    1.02
    lins
    1.00
     mornings
    1.00
     throughout
    1.00
     until
    0.98
     commute
    0.98
    brates
    0.95
    Activations Density 0.591%

    No Known Activations