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 24576
    5. 8-RES_FS24576-JB
    6. 12364
    Prev
    Next
    INDEX
    Explanations

    sports events or scores related to specific teams or universities

    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
    481
    +0.19
    0.9%
    96
    +0.12
    0.6%
    7
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.19
    0.04
    220
    +0.12
    0.02
    548
    +0.11
    0.01
    Negative Logits
    ling
    -1.04
    liness
    -0.89
    lings
    -0.82
    ening
    -0.81
    maid
    -0.81
    ker
    -0.80
    cloth
    -0.79
    yg
    -0.79
    bags
    -0.78
    wan
    -0.75
    POSITIVE LOGITS
    iances
    0.81
    ANCE
    0.69
    inated
    0.68
    é¾
    0.67
    ria
    0.65
    anced
    0.64
    querque
    0.64
     sqor
    0.64
    heast
    0.63
    abama
    0.62
    Activations Density 0.091%

    No Known Activations