© 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. 10298
    Prev
    Next
    INDEX
    Explanations

    information related to brewing beer and administrative terms

    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
    447
    +0.21
    1.0%
    762
    +0.10
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.21
    0.07
    461
    +0.10
    0.05
    439
    +0.10
    0.06
    Negative Logits
    Tes
    -0.77
    Ay
    -0.71
    senal
    -0.62
     Glas
    -0.60
    Fla
    -0.60
    Eva
    -0.59
    Ire
    -0.58
    Awesome
    -0.56
    elin
    -0.55
    Cruz
    -0.55
    POSITIVE LOGITS
     refers
    1.40
     consists
    1.31
     involves
    1.20
     entails
    1.19
     implies
    1.19
     encompasses
    1.13
     signifies
    1.11
     represents
    1.08
     means
    1.05
     occurs
    1.04
    Activations Density 0.804%

    No Known Activations