© 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 EvalsExportsinterp-engineNEWAPI 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. 11086
    Prev
    Next
    INDEX
    Explanations

    key phrases related to population size or demographic changes

    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
    288
    +0.29
    0.9%
    99
    +0.25
    0.8%
    89
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.29
    0.07
    575
    +0.25
    0.07
    99
    +0.19
    0.05
    Negative Logits
    href
    -1.33
    vell
    -1.25
    ery
    -1.19
    amina
    -1.18
    uran
    -1.17
    ĪĴ
    -1.17
    rah
    -1.15
    itude
    -1.13
    awaru
    -1.13
    urn
    -1.13
    POSITIVE LOGITS
     genetics
    1.19
     centers
    1.14
    wide
    1.13
    atics
    1.11
     residing
    1.10
     density
    1.05
    houses
    1.00
     inhab
    0.97
    iatrics
    0.94
     attributable
    0.93
    Activations Density 0.882%

    No Known Activations