© 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. 7863
    Prev
    Next
    INDEX
    Explanations

    phrases related to authority and control

    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
    552
    +0.18
    0.6%
    477
    +0.15
    0.5%
    393
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.18
    0.07
    123
    +0.15
    0.07
    552
    +0.15
    0.07
    Negative Logits
    xual
    -1.27
    catentry
    -1.02
    abilia
    -1.00
    caster
    -0.95
    iosity
    -0.94
    tes
    -0.93
    oga
    -0.91
    CHAT
    -0.90
    icides
    -0.90
    uracy
    -0.89
    POSITIVE LOGITS
     jeopardy
    1.37
    pload
    1.16
    ixon
    1.02
     orbit
    1.01
    ilts
    0.98
     peril
    0.97
    accessible
    0.96
    ipolar
    0.93
     place
    0.93
     limbo
    0.91
    Activations Density 1.175%

    No Known Activations