© 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 12288
    5. 8-RES_FS12288-JB
    6. 857
    Prev
    Next
    INDEX
    Explanations

    words related to natural disasters and geographical 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_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    549
    +0.13
    0.6%
    659
    +0.10
    0.5%
    643
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.04
    232
    +0.10
    0.03
    343
    +0.10
    0.03
    Negative Logits
    Ö¼
    -0.73
     Collider
    -0.68
     laureate
    -0.66
    ãĤ£
    -0.64
    ORPG
    -0.64
     dividend
    -0.62
    builders
    -0.60
    ãĤ¡
    -0.59
     Tempest
    -0.57
     Founders
    -0.57
    POSITIVE LOGITS
    unin
    1.20
    umar
    1.18
    istani
    1.13
    ota
    1.05
    arak
    1.03
    ansas
    0.99
    rish
    0.99
    shi
    0.93
    uten
    0.93
    ernel
    0.91
    Activations Density 0.076%

    No Known Activations