© 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. 18873
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal experiences and opinions

    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
    107
    +0.12
    0.6%
    314
    +0.12
    0.5%
    160
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    107
    +0.12
    0.03
    160
    +0.12
    0.03
    675
    +0.12
    0.03
    Negative Logits
     topic
    -0.78
     metic
    -0.73
     limb
    -0.72
     mathemat
    -0.72
     dossier
    -0.71
     detail
    -0.70
     territorial
    -0.69
     stake
    -0.68
     vulner
    -0.68
     contested
    -0.68
    POSITIVE LOGITS
    ï¸ı
    1.22
    ï¸
    0.96
    there
    0.95
    RIP
    0.89
    ãĥĥãĥī
    0.87
    âĹ¼
    0.87
    nob
    0.86
    sure
    0.85
    everyone
    0.85
    hey
    0.84
    Activations Density 0.030%

    No Known Activations