© 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 49152
    9. 8-RES_FS49152-JB
    11. 26508
    Prev
    Next
    INDEX
    Explanations

    words related to financial losses or crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    373
    +0.11
    0.5%
    397
    +0.09
    0.4%
    744
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.11
    0.02
    373
    +0.09
    -0.00
    397
    +0.09
    0.01
    Negative Logits
    ©¶æ
    -0.85
    ħĭ
    -0.81
    querque
    -0.77
    -+-+
    -0.75
    vantage
    -0.71
    ij士
    -0.70
    ãĥ¼ãĥĨ
    -0.70
    ĪĴ
    -0.68
    senal
    -0.65
    elsius
    -0.65
    POSITIVE LOGITS
    ipeg
    1.24
    cases
    0.83
    makers
    0.79
    wright
    0.77
    burg
    0.77
    lust
    0.75
    bucks
    0.74
    maker
    0.71
    ows
    0.71
    ful
    0.70
    Activations Density 0.015%

    No Known Activations