© 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. 169
    Prev
    Next
    INDEX
    Explanations

    information related to announcements or promotions such as event details, product specifications, and community activities

    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
    480
    +0.80
    16.4%
    326
    +0.09
    1.8%
    351
    +0.04
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.80
    0.19
    266
    +0.09
    0.65
    276
    +0.04
    0.35
    Negative Logits
    soDeliveryDate
    -0.14
     Cosponsors
    -0.13
    NetMessage
    -0.13
    pmwiki
    -0.12
     Marketable
    -0.12
    hov
    -0.12
    interrupted
    -0.12
    alcohol
    -0.12
    enforcement
    -0.12
    ciation
    -0.11
    POSITIVE LOGITS
    aeper
    0.12
    PLIED
    0.10
    rette
    0.10
    -|
    0.10
     mines
    0.10
     Cutter
    0.10
     extensively
    0.09
    pty
    0.09
     Channel
    0.09
     machine
    0.09
    Activations Density 33.486%

    No Known Activations