© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7498
    Prev
    Next
    INDEX
    Explanations

    references to corporate entities and activities within various contexts

    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
    167
    +0.15
    0.7%
    288
    +0.14
    0.6%
    644
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.15
    0.02
    167
    +0.14
    0.01
    656
    +0.10
    0.02
    Negative Logits
    range
    -0.75
    icans
    -0.74
    theless
    -0.74
    uberty
    -0.73
    xual
    -0.72
    lessly
    -0.72
    itives
    -0.70
    Detailed
    -0.69
    finding
    -0.69
    liness
    -0.69
    POSITIVE LOGITS
     sponsorship
    1.00
     executives
    0.96
    porate
    0.94
    orpor
    0.92
     espionage
    0.89
     restructuring
    0.89
     governance
    0.89
     sponsors
    0.85
     outsourcing
    0.83
     profits
    0.83
    Activations Density 0.030%

    No Known Activations