© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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 Local
    9. 6-RES_SCL-AJT
    11. 13134
    Prev
    Next
    INDEX
    Explanations

    academic and educational terms related to lectures, teaching, seminars, and academia

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    Neuron Alignment
    Index
    Value
    % of L₁
    235
    +0.09
    0.7%
    679
    +0.09
    0.7%
    526
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.17
    235
    +0.09
    0.10
    326
    +0.06
    0.14
    Negative Logits
    odka
    -0.50
     Scotia
    -0.43
    anking
    -0.41
    bably
    -0.37
    uilt
    -0.37
    mental
    -0.37
    markets
    -0.36
    nergy
    -0.36
     Cyprus
    -0.35
    fw
    -0.35
    POSITIVE LOGITS
     Lect
    0.60
     lecture
    0.47
    iasis
    0.46
    ysis
    0.46
    ĸļ
    0.46
    erer
    0.45
    hemat
    0.45
     lectures
    0.44
    ures
    0.44
    ç·
    0.43
    Activations Density 3.636%

    No Known Activations