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. 43227
    Prev
    Next
    INDEX
    Explanations

    emotional states characterized by distress, concern, or agitation

    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
    362
    +0.13
    0.6%
    242
    +0.12
    0.6%
    593
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.13
    0.03
    453
    +0.12
    0.03
    655
    +0.11
    0.03
    Negative Logits
    artifacts
    -0.86
    sites
    -0.77
    safe
    -0.77
    Jump
    -0.75
    inctions
    -0.74
    lished
    -0.73
    orthy
    -0.73
    Unique
    -0.73
    itism
    -0.72
    Downloadha
    -0.72
    POSITIVE LOGITS
     onlook
    1.10
     populace
    0.96
     masses
    0.95
    ness
    0.91
     plea
    0.89
     young
    0.86
     demeanor
    0.85
     youngsters
    0.85
     souls
    0.83
     tone
    0.81
    Activations Density 0.086%

    No Known Activations