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 49152
    5. 8-RES_FS49152-JB
    6. 41537
    Prev
    Next
    INDEX
    Explanations

    mentions of specific plant-related items and their uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    694
    +0.11
    0.5%
    238
    +0.09
    0.4%
    649
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.11
    0.04
    530
    +0.09
    0.03
    241
    +0.09
    0.04
    Negative Logits
    Ô
    -0.63
    ãĤ¼ãĤ¦ãĤ¹
    -0.61
    ccording
    -0.59
     tremend
    -0.59
    âķIJâķIJ
    -0.58
    ij士
    -0.56
    .""
    -0.54
    Ń·
    -0.54
     guiActiveUn
    -0.53
    »
    -0.53
    POSITIVE LOGITS
    ↵
    1.74
    <|endoftext|>
    1.25
    ↵↵
    1.14
    SPONSORED
    1.08
    ;}
    0.69
     TBA
    0.68
    [/
    0.66
    ↵Âł
    0.65
    ;
    0.62
     Boxing
    0.59
    Activations Density 0.173%

    No Known Activations