© 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. 7408
    Prev
    Next
    INDEX
    Explanations

    verbs related to proposing, recommending, or predicting actions

    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
    447
    +0.18
    0.8%
    276
    +0.11
    0.5%
    421
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.18
    0.04
    69
    +0.11
    0.04
    70
    +0.10
    0.04
    Negative Logits
    DragonMagazine
    -0.91
    ï¸ı
    -0.78
    agent
    -0.74
    sworth
    -0.74
    facebook
    -0.74
    \/\/
    -0.74
    omaly
    -0.72
    super
    -0.72
    kie
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.71
    POSITIVE LOGITS
     abandoning
    0.93
     arming
    0.88
     sacrificing
    0.84
     alternatives
    0.83
     postp
    0.82
     removing
    0.82
     eliminating
    0.81
     stricter
    0.80
     abol
    0.79
     something
    0.79
    Activations Density 0.198%

    No Known Activations