© 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. 18954
    Prev
    Next
    INDEX
    Explanations

    natural disaster-related terms

    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
    27
    +0.11
    0.5%
    129
    +0.10
    0.5%
    198
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    27
    +0.11
    0.03
    129
    +0.10
    0.03
    326
    +0.10
    0.02
    Negative Logits
    iture
    -0.79
     Token
    -0.74
     Founding
    -0.74
     Ethics
    -0.74
     Employee
    -0.72
    JECT
    -0.72
     Lives
    -0.71
    Priv
    -0.68
     Intellectual
    -0.67
    prison
    -0.66
    POSITIVE LOGITS
     gust
    1.16
     winds
    1.12
     blowing
    1.05
     blew
    0.98
     swept
    0.96
     Irma
    0.96
     raged
    0.91
     roared
    0.89
     roar
    0.89
     roaring
    0.88
    Activations Density 0.079%

    No Known Activations