© 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. 352
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussing or expressing opinions on a topic

    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
    270
    +0.12
    0.5%
    155
    +0.12
    0.5%
    723
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.12
    0.06
    723
    +0.12
    0.05
    270
    +0.10
    0.04
    Negative Logits
    OGR
    -0.82
    hesis
    -0.81
    hiba
    -0.77
    quez
    -0.74
    kai
    -0.73
    terness
    -0.72
    aic
    -0.71
    nis
    -0.71
    cue
    -0.70
    chnology
    -0.69
    POSITIVE LOGITS
     how
    0.98
     reforming
    0.95
     improving
    0.90
     overcoming
    0.85
     wanting
    0.85
     quitting
    0.82
     whether
    0.82
     preserving
    0.82
     achieving
    0.81
     getting
    0.80
    Activations Density 0.167%

    No Known Activations