© 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. 1341
    Prev
    Next
    INDEX
    Explanations

    words related to protection or safety

    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
    713
    +0.13
    0.6%
    362
    +0.12
    0.5%
    711
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.07
    711
    +0.12
    0.04
    713
    +0.12
    0.05
    Negative Logits
    Downloadha
    -0.83
    lessly
    -0.80
    olen
    -0.78
    cedented
    -0.78
    eem
    -0.78
    buck
    -0.76
    ruary
    -0.75
    igon
    -0.74
    uate
    -0.74
    mere
    -0.74
    POSITIVE LOGITS
     qualities
    0.97
     activity
    0.90
     factors
    0.87
     measures
    0.87
     behaviour
    0.84
     aspects
    0.83
     impulse
    0.83
     aspect
    0.83
     impulses
    0.83
     factor
    0.81
    Activations Density 0.332%

    No Known Activations