© 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. 35706
    Prev
    Next
    INDEX
    Explanations

    functions or elements related to communication or interaction with sockets in software or hardware systems

    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
    +0.15
    0.8%
    326
    +0.14
    0.7%
    361
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.22
    288
    +0.14
    0.21
    178
    +0.11
    0.14
    Negative Logits
     Lys
    -0.66
    birth
    -0.64
    hig
    -0.63
    ATHER
    -0.62
    enez
    -0.58
    YC
    -0.56
     Ames
    -0.55
     Hum
    -0.55
    gary
    -0.55
     Whitman
    -0.55
    POSITIVE LOGITS
     sockets
    0.97
     socket
    0.97
     Socket
    0.88
    socket
    0.87
     wrench
    0.84
    chio
    0.75
    rings
    0.75
    acles
    0.71
    ocket
    0.70
    urrencies
    0.68
    Activations Density 7.727%

    No Known Activations