© 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 24576
    9. 8-RES_FS24576-JB
    11. 7239
    Prev
    Next
    INDEX
    Explanations

    the preposition 'to' followed by a verb

    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
    718
    +0.12
    0.5%
    608
    +0.12
    0.5%
    306
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    49
    +0.12
    0.03
    105
    +0.12
    0.02
    718
    +0.11
    0.03
    Negative Logits
    soDeliveryDate
    -0.72
    river
    -0.68
     Settlement
    -0.66
    Required
    -0.65
     Kinnikuman
    -0.65
     Worth
    -0.63
    packing
    -0.61
    written
    -0.60
     Trooper
    -0.59
    abiding
    -0.59
    POSITIVE LOGITS
     remind
    1.10
     hear
    1.05
     pretend
    1.03
     see
    0.98
     speculate
    0.98
     emulate
    0.97
     tease
    0.96
     engage
    0.93
     visualize
    0.93
     keep
    0.93
    Activations Density 0.048%

    No Known Activations