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. 1481
    Prev
    Next
    INDEX
    Explanations

    phrases related to protests and clashes with authorities

    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
    516
    +0.09
    0.4%
    260
    +0.09
    0.4%
    105
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.09
    0.05
    260
    +0.09
    0.05
    505
    +0.09
    0.04
    Negative Logits
     immortality
    -0.92
    ģĸ
    -0.85
    Reviewer
    -0.76
    Heart
    -0.76
    perfect
    -0.74
     Lifetime
    -0.73
    arenthood
    -0.73
    Perfect
    -0.73
    Parent
    -0.72
    ãĤ´ãĥ³
    -0.72
    POSITIVE LOGITS
     protesters
    1.17
     demonstrators
    1.17
     barric
    1.14
     chanting
    1.13
     gunmen
    1.12
     riot
    1.11
     clashes
    1.08
     gunfire
    1.04
     assailants
    1.04
     shouting
    1.04
    Activations Density 0.434%

    No Known Activations