© 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. 11286
    Prev
    Next
    INDEX
    Explanations

    questions asking what actions to take in various situations

    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
    78
    +0.16
    0.5%
    679
    +0.16
    0.5%
    20
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.16
    0.07
    206
    +0.16
    0.06
    452
    +0.15
    0.06
    Negative Logits
    theless
    -1.25
     Frie
    -1.23
     Entered
    -1.22
    Board
    -1.02
     Gork
    -1.00
    mares
    -0.99
    inently
    -0.98
     tongues
    -0.96
    ware
    -0.94
     Indust
    -0.94
    POSITIVE LOGITS
    pez
    1.48
    berman
    1.22
    ledge
    1.06
    INGS
    1.06
    ogue
    1.04
    ggy
    1.04
    atives
    1.03
    omsday
    1.01
    ison
    1.00
    omething
    0.98
    Activations Density 0.532%

    No Known Activations