© 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. 35365
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly names of individuals, organizations, places, and titles

    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
    10
    +0.09
    0.5%
    755
    +0.09
    0.5%
    343
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.09
    0.20
    447
    +0.09
    0.23
    64
    +0.09
    -0.21
    Negative Logits
    âĸ¬
    -0.78
    ++++++++++++++++
    -0.63
     congr
    -0.61
    bourg
    -0.61
     centrif
    -0.60
    ++++
    -0.57
    Ú
    -0.57
    士
    -0.56
     Practices
    -0.56
     Franch
    -0.56
    POSITIVE LOGITS
     ow
    0.99
    ls
    0.95
    ahoo
    0.95
    yssey
    0.93
    swick
    0.90
    keye
    0.84
    ecause
    0.80
    terness
    0.78
    chemy
    0.77
    warts
    0.76
    Activations Density 9.534%

    No Known Activations