Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 23818
    Prev
    Next
    INDEX
    Explanations

    references to violence and non-violent actions

    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
    637
    +0.12
    0.5%
    582
    +0.10
    0.5%
    444
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.01
    685
    +0.10
    0.01
    660
    +0.10
    0.01
    Negative Logits
     Tycoon
    -0.76
    GPU
    -0.74
     Viz
    -0.72
    ween
    -0.70
    eus
    -0.66
     Collector
    -0.66
    mal
    -0.66
    resses
    -0.66
    Crash
    -0.64
     Kou
    -0.64
    POSITIVE LOGITS
    iferation
    0.89
     nonviolent
    0.84
    istance
    0.80
    vernment
    0.79
    violent
    0.78
    ances
    0.78
     minded
    0.77
     endeavor
    0.75
    ance
    0.74
     exercise
    0.72
    Activations Density 0.013%

    No Known Activations