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. 10954
    Prev
    Next
    INDEX
    Explanations

    specific times in a 12-hour notation with p.m. markers

    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
    373
    +0.15
    0.7%
    331
    +0.09
    0.4%
    460
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    460
    +0.15
    0.03
    667
    +0.09
    0.03
    296
    +0.08
    0.03
    Negative Logits
    lessly
    -0.70
    alogy
    -0.65
    asel
    -0.64
    hered
    -0.60
    urer
    -0.59
    itives
    -0.59
    agna
    -0.58
    sole
    -0.58
    saf
    -0.58
     Definitive
    -0.57
    POSITIVE LOGITS
    pm
    1.28
     pm
    1.14
    PM
    1.13
    AM
    0.97
    GMT
    0.93
     PST
    0.93
     noon
    0.90
     PDT
    0.88
     PM
    0.88
     hrs
    0.87
    Activations Density 0.044%

    No Known Activations