© 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. 1203
    Prev
    Next
    INDEX
    Explanations

    expressions related to opinions, statements, and debates

    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
    481
    +0.11
    0.5%
    449
    +0.10
    0.5%
    614
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.11
    0.05
    449
    +0.10
    0.05
    393
    +0.10
    0.07
    Negative Logits
     Unsure
    -0.60
    etting
    -0.60
     WATCHED
    -0.59
    Blocks
    -0.59
     Disable
    -0.58
     peek
    -0.58
     Advertisement
    -0.57
    IDER
    -0.57
    Vers
    -0.57
    Alert
    -0.57
    POSITIVE LOGITS
     humankind
    1.05
    ankind
    0.96
    everyone
    0.96
     anybody
    0.94
     yours
    0.93
     theirs
    0.91
     mankind
    0.91
     society
    0.90
     others
    0.90
     whoever
    0.88
    Activations Density 0.484%

    No Known Activations