© 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. 12060
    Prev
    Next
    INDEX
    Explanations

    comments or examples suggesting hypothetical scenarios or assumptions

    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
    514
    +0.17
    0.5%
    453
    +0.16
    0.5%
    267
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.17
    0.03
    305
    +0.16
    0.02
    538
    +0.15
    0.02
    Negative Logits
    taboola
    -1.35
    Ô
    -1.29
    TPPStreamerBot
    -1.14
    estyles
    -1.09
    ocene
    -1.06
    zag
    -1.01
    tyard
    -1.01
    EStreamFrame
    -0.99
    ifact
    -0.99
    olesc
    -0.98
    POSITIVE LOGITS
     Seymour
    1.13
     ye
    1.09
     hello
    1.03
     you
    1.01
     Yi
    0.95
     yourself
    0.92
     ya
    0.91
     nothing
    0.91
    ings
    0.89
    yon
    0.88
    Activations Density 0.195%

    No Known Activations