© 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. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 8694
    Prev
    Next
    INDEX
    Explanations

    layers in a sequence of instructions or information

    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
    99
    +0.10
    0.4%
    523
    +0.09
    0.4%
    288
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    41
    +0.10
    0.01
    678
    +0.09
    0.01
    99
    +0.09
    0.01
    Negative Logits
    ãĥīãĥ©
    -0.86
    lishing
    -0.77
    date
    -0.77
    itarian
    -0.76
    ILLE
    -0.74
    orie
    -0.73
     Predators
    -0.73
    etheus
    -0.71
    speaking
    -0.70
    photo
    -0.69
    POSITIVE LOGITS
     layers
    1.32
     layer
    1.12
     thickness
    1.08
     opacity
    0.81
    layer
    0.81
     layered
    0.79
     separ
    0.79
     coats
    0.76
     refinement
    0.76
     veil
    0.75
    Activations Density 0.022%

    No Known Activations