© 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 12288
    9. 8-RES_FS12288-JB
    11. 498
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal cases and public locations

    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
    110
    +0.10
    0.5%
    680
    +0.10
    0.4%
    585
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    585
    +0.10
    0.08
    110
    +0.10
    0.06
    65
    +0.10
    0.06
    Negative Logits
    uria
    -0.90
    ourning
    -0.80
    verbs
    -0.77
    thia
    -0.76
    -+-+
    -0.76
    riel
    -0.75
    ocrates
    -0.74
    cedes
    -0.72
    requires
    -0.72
    ivably
    -0.71
    POSITIVE LOGITS
     debacle
    1.10
     Foundation
    1.07
     fiasco
    1.04
     saga
    1.00
     affair
    0.99
     logo
    0.98
     playbook
    0.94
     era
    0.92
     Massacre
    0.91
     Declaration
    0.90
    Activations Density 0.626%

    No Known Activations