© 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. 39888
    Prev
    Next
    INDEX
    Explanations

    and interact with forms for various purposes like applications, submissions, and registrations

    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
    447
    +0.14
    0.8%
    388
    +0.14
    0.8%
    651
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    388
    +0.14
    0.12
    707
    +0.14
    0.07
    651
    +0.10
    0.08
    Negative Logits
    iband
    -0.61
     Loss
    -0.56
    velength
    -0.56
     Creatures
    -0.55
     Flavoring
    -0.55
    frey
    -0.54
    Domin
    -0.53
    tsky
    -0.52
     Nath
    -0.52
    ankind
    -0.52
    POSITIVE LOGITS
     paperwork
    0.79
     mailed
    0.75
     payable
    0.69
     PayPal
    0.66
     spreadsheet
    0.65
     submission
    0.64
    naires
    0.63
     petitions
    0.63
     registration
    0.61
     Coinbase
    0.61
    Activations Density 9.791%

    No Known Activations