© 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. 22221
    Prev
    Next
    INDEX
    Explanations

    terms associated with financial risks and hazards

    oai_token-act-pair · gpt-4o-miniTriggered 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
    195
    +0.14
    0.6%
    285
    +0.11
    0.5%
    511
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.14
    0.04
    285
    +0.11
    0.02
    247
    +0.11
    0.03
    Negative Logits
    gdala
    -0.81
    atters
    -0.72
    riot
    -0.70
     Bed
    -0.67
    poons
    -0.66
    gian
    -0.65
    issance
    -0.63
    ergy
    -0.63
    Dispatch
    -0.62
    uania
    -0.62
    POSITIVE LOGITS
     aversion
    0.95
    taking
    0.92
     incurred
    0.88
    iest
    0.86
     mitigation
    0.86
     posed
    0.82
     factors
    0.81
    staking
    0.81
     avoidance
    0.79
    iness
    0.76
    Activations Density 0.033%

    No Known Activations