© 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 3072
    9. 8-RES_FS3072-JB
    11. 679
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    480
    +0.63
    3.8%
    420
    +0.16
    0.9%
    447
    +0.15
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.63
    0.05
    266
    +0.16
    0.24
    724
    +0.15
    0.16
    Negative Logits
    REDACTED
    -0.58
    çīĪ
    -0.57
    Had
    -0.56
    Was
    -0.55
    _.
    -0.54
    was
    -0.53
    Finish
    -0.53
    later
    -0.51
    endum
    -0.51
    Attach
    -0.50
    POSITIVE LOGITS
     often
    0.77
    often
    0.75
     routinely
    0.74
     economies
    0.74
     nowadays
    0.71
     disproportionately
    0.69
    pmwiki
    0.67
     frequently
    0.66
     sometimes
    0.66
     environments
    0.65
    Activations Density 7.222%

    No Known Activations