© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 18936
    Prev
    Next
    INDEX
    Explanations

    the word "so" when used emphatically to express a result or consequence

    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
    509
    +0.10
    0.4%
    540
    +0.09
    0.4%
    699
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.10
    0.02
    540
    +0.09
    0.02
    699
    +0.09
    0.01
    Negative Logits
     Hunters
    -0.64
     Lau
    -0.63
    aughed
    -0.60
    works
    -0.60
     Kang
    -0.59
     Concepts
    -0.59
    ²
    -0.58
     Dreams
    -0.58
     Neighborhood
    -0.58
     Moving
    -0.58
    POSITIVE LOGITS
    oner
    1.03
     anonymously
    0.93
    zin
    0.82
     cheaply
    0.80
     willingly
    0.80
    othe
    0.79
     voluntarily
    0.77
     legally
    0.77
     reluctantly
    0.76
    ----------------------------------------------------------------
    0.75
    Activations Density 0.019%

    No Known Activations