© 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. 833
    Prev
    Next
    INDEX
    Explanations

    leave empty fields in an email form

    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
    517
    +0.10
    0.6%
    302
    +0.09
    0.5%
    569
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    194
    +0.10
    0.03
    521
    +0.09
    0.02
    530
    +0.08
    0.02
    Negative Logits
    ettings
    -0.64
    abase
    -0.63
    ettlement
    -0.57
    MpServer
    -0.55
    iants
    -0.53
    models
    -0.53
     Models
    -0.53
    ibles
    -0.52
    Crew
    -0.52
    ynt
    -0.52
    POSITIVE LOGITS
    toggle
    0.67
    reset
    0.66
     Emerson
    0.58
    QUI
    0.56
    ALSE
    0.55
    PLIED
    0.55
     HuffPost
    0.54
    WARN
    0.53
     mu
    0.53
    %]
    0.52
    Activations Density 0.130%

    No Known Activations