Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 8100
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating pursuit or action towards a target

    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
    686
    +0.11
    0.5%
    634
    +0.11
    0.5%
    218
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.11
    0.01
    218
    +0.11
    0.01
    329
    +0.10
    0.01
    Negative Logits
    Released
    -0.87
    arnaev
    -0.76
    osuke
    -0.73
     guiActiveUn
    -0.71
    aez
    -0.70
    omsky
    -0.69
    eller
    -0.69
    kept
    -0.68
    ascript
    -0.68
    hes
    -0.67
    POSITIVE LOGITS
    market
    0.71
     somebody
    0.69
     supper
    0.65
     scraps
    0.63
    lain
    0.62
     steak
    0.60
     someone
    0.60
     something
    0.60
    wards
    0.60
     lunch
    0.60
    Activations Density 0.032%

    No Known Activations