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

    Neuronpedia

    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. 7933
    Prev
    Next
    INDEX
    Explanations

    mentions of legal terms or legislative contexts related to decision-making processes

    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
    288
    +0.18
    0.8%
    612
    +0.10
    0.5%
    99
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.18
    0.01
    752
    +0.10
    0.01
    612
    +0.10
    0.01
    Negative Logits
    geon
    -0.98
    gered
    -0.96
    paces
    -0.85
    steen
    -0.82
    gers
    -0.81
    ear
    -0.80
    bel
    -0.79
    bring
    -0.74
    kers
    -0.73
    baugh
    -0.73
    POSITIVE LOGITS
     Commonwealth
    0.97
     Scientific
    0.83
    wide
    0.81
     Edison
    0.79
     Institute
    0.77
     Papers
    0.74
     Reserve
    0.74
    enary
    0.74
    ortium
    0.73
     Coast
    0.73
    Activations Density 0.025%

    No Known Activations