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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 49152
    9. 8-RES_FS49152-JB
    11. 41758
    Prev
    Next
    INDEX
    Explanations

    technical terms related to network configuration and device identification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    255
    +0.15
    0.7%
    522
    +0.11
    0.5%
    737
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.15
    0.02
    220
    +0.11
    0.01
    326
    +0.10
    0.01
    Negative Logits
    ndra
    -0.93
    hur
    -0.88
    soDeliveryDate
    -0.81
    issance
    -0.78
    kus
    -0.77
    herty
    -0.73
    ossom
    -0.73
    itamin
    -0.73
    othe
    -0.72
    isner
    -0.72
    POSITIVE LOGITS
     forwarding
    1.04
    addr
    0.96
    names
    0.94
     addr
    0.89
     Address
    0.89
     IPv
    0.88
     address
    0.87
     hash
    0.84
     443
    0.84
     URI
    0.82
    Activations Density 0.026%

    No Known Activations