© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 4487
    Prev
    Next
    INDEX
    Explanations

    words related to metal or tin

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    386
    +0.11
    0.5%
    326
    +0.09
    0.4%
    535
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    67
    +0.09
    0.01
    535
    +0.09
    0.01
    Negative Logits
    enance
    -0.99
     Emanuel
    -0.65
     Parish
    -0.64
    dL
    -0.64
     Springer
    -0.64
     Gamergate
    -0.63
     Wiley
    -0.63
    llan
    -0.60
     Accountability
    -0.60
     Vector
    -0.58
    POSITIVE LOGITS
    kered
    1.27
    ned
    1.18
    oco
    1.07
    icum
    1.06
    sel
    1.05
    uous
    1.01
    iqu
    0.98
     oxide
    0.96
    omial
    0.92
    iple
    0.92
    Activations Density 0.022%

    No Known Activations