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. 18489
    Prev
    Next
    INDEX
    Explanations

    information related to event locations and details

    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
    119
    +0.11
    0.5%
    669
    +0.10
    0.5%
    629
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.04
    640
    +0.10
    0.04
    285
    +0.10
    0.01
    Negative Logits
     spons
    -0.87
    ilater
    -0.77
     laun
    -0.76
    ortium
    -0.74
     conclud
    -0.71
    idden
    -0.71
     authorised
    -0.70
    psey
    -0.70
    ascus
    -0.70
    usalem
    -0.69
    POSITIVE LOGITS
    notations
    0.82
     Dragonbound
    0.80
     Subtle
    0.78
    sounding
    0.74
     (>
    0.73
    Medium
    0.73
    pants
    0.72
    enough
    0.71
    yet
    0.70
    Characters
    0.69
    Activations Density 0.148%

    No Known Activations