© 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. 23889
    Prev
    Next
    INDEX
    Explanations

    events related to missing persons and their discovery

    oai_token-act-pair · gpt-4o-miniTriggered 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
    430
    +0.14
    0.6%
    639
    +0.11
    0.5%
    565
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.14
    0.06
    639
    +0.11
    0.03
    430
    +0.10
    0.06
    Negative Logits
     awarding
    -0.88
     Equal
    -0.76
     synerg
    -0.74
     quotas
    -0.73
     applaud
    -0.73
     semif
    -0.72
     leverage
    -0.71
    iron
    -0.71
     sexist
    -0.69
     sexism
    -0.69
    POSITIVE LOGITS
     whereabouts
    1.52
     vanished
    1.36
     disappearance
    1.33
     disappeared
    1.32
     abducted
    1.17
     sightings
    1.10
     mysteriously
    1.10
     abduction
    1.03
     disappear
    1.03
     wandering
    0.99
    Activations Density 0.492%

    No Known Activations