© 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. 1293
    Prev
    Next
    INDEX
    Explanations

    phrases related to downloading content such as files, apps, and reports

    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
    152
    +0.13
    0.6%
    426
    +0.11
    0.5%
    373
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    592
    +0.13
    0.05
    426
    +0.11
    0.05
    273
    +0.10
    0.05
    Negative Logits
    cffffcc
    -0.63
     disg
    -0.63
    mith
    -0.62
    */(
    -0.62
    ÏĢ
    -0.62
    pires
    -0.62
     tandem
    -0.61
    ../
    -0.61
     respectively
    -0.60
     territ
    -0.59
    POSITIVE LOGITS
    ing
    1.16
     Your
    0.93
    ed
    0.90
     Details
    0.90
    ership
    0.88
     Yourself
    0.88
     Quote
    0.87
     Results
    0.85
     Links
    0.85
    tainment
    0.85
    Activations Density 0.240%

    No Known Activations