© 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 Local
    9. 6-RES_SCL-AJT
    11. 36718
    Prev
    Next
    INDEX
    Explanations

    technical terms or jargon related to computer programming and mathematics

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    535
    +0.10
    0.6%
    159
    +0.08
    0.5%
    52
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    699
    +0.10
    0.03
    614
    +0.08
    0.03
    406
    +0.08
    0.09
    Negative Logits
    DonaldTrump
    -0.56
    Adapt
    -0.55
    ZI
    -0.53
    UTE
    -0.53
    NRS
    -0.51
    externalActionCode
    -0.50
    IPS
    -0.50
    INT
    -0.47
    ADS
    -0.47
     Patron
    -0.47
    POSITIVE LOGITS
    iverse
    0.56
    rome
    0.56
    ifying
    0.56
    ding
    0.55
    ifiable
    0.55
    est
    0.55
    oom
    0.55
    ollah
    0.53
    esty
    0.53
    er
    0.53
    Activations Density 7.439%

    No Known Activations