© 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. 6132
    Prev
    Next
    INDEX
    Explanations

    names of bacteria and related technical terms in biology

    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
    201
    +0.17
    0.6%
    211
    +0.16
    0.6%
    515
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.11
    57
    +0.16
    0.07
    747
    +0.14
    0.05
    Negative Logits
    urities
    -1.02
    terday
    -0.95
    benefit
    -0.89
    othal
    -0.86
    otent
    -0.85
    BOOK
    -0.82
    uncture
    -0.81
    isting
    -0.80
    ory
    -0.80
    UAL
    -0.80
    POSITIVE LOGITS
    keley
    1.38
    rien
    1.29
    ger
    1.24
    lus
    1.17
    rigan
    1.01
    icy
    1.01
    deen
    0.98
    lins
    0.97
    gers
    0.97
    LIN
    0.96
    Activations Density 2.262%

    No Known Activations