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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 12288
    5. 8-RES_FS12288-JB
    6. 9918
    Prev
    Next
    INDEX
    Explanations

    phrases related to time durations or financial amounts

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    481
    +0.15
    0.7%
    71
    +0.12
    0.6%
    742
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.15
    0.04
    39
    +0.12
    0.04
    651
    +0.12
    0.04
    Negative Logits
    hod
    -0.68
    actionDate
    -0.66
    ablished
    -0.65
    enth
    -0.64
    achus
    -0.63
    enes
    -0.63
    meier
    -0.62
    rities
    -0.61
    soType
    -0.60
    pty
    -0.60
    POSITIVE LOGITS
     thereafter
    0.97
     (~
    0.81
     (£
    0.81
     ($
    0.74
     ago
    0.71
     basis
    0.69
    wage
    0.69
     âĪ
    0.68
    âĪĴ
    0.67
     includ
    0.66
    Activations Density 0.097%

    No Known Activations