© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 39640
    Prev
    Next
    INDEX
    Explanations

    technical terms, model names, and terms related to academic studies

    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
    635
    +0.09
    0.5%
    438
    +0.08
    0.5%
    503
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.09
    0.20
    326
    +0.08
    0.20
    291
    +0.08
    0.08
    Negative Logits
    akov
    -0.65
    aret
    -0.63
    ramid
    -0.62
    creen
    -0.59
    ographed
    -0.55
    kaya
    -0.54
    inates
    -0.54
    eer
    -0.53
    eers
    -0.53
    ograp
    -0.51
    POSITIVE LOGITS
     DW
    0.62
    izoph
    0.53
    BY
    0.53
    ipeg
    0.52
    429
    0.51
    IGHT
    0.51
    ifts
    0.50
    ORD
    0.50
    icious
    0.48
    ifter
    0.48
    Activations Density 6.875%

    No Known Activations