© 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. 7352
    Prev
    Next
    INDEX
    Explanations

    references to controversial incidents or events

    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
    105
    +0.13
    0.6%
    98
    +0.11
    0.5%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    98
    +0.13
    0.07
    105
    +0.11
    0.05
    703
    +0.10
    0.05
    Negative Logits
    tick
    -0.79
     isEnabled
    -0.75
    Typ
    -0.75
    aez
    -0.74
    psy
    -0.74
    minus
    -0.73
    email
    -0.72
    typ
    -0.72
    et
    -0.70
    Probably
    -0.70
    POSITIVE LOGITS
     discovering
    1.02
     noticing
    0.90
     seeing
    0.88
     revelations
    0.86
     failing
    0.86
     witnessing
    0.85
     announcing
    0.85
    math
    0.84
     repeated
    0.84
     encountering
    0.83
    Activations Density 0.102%

    No Known Activations