© 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 24576
    9. 8-RES_FS24576-JB
    11. 18688
    Prev
    Next
    INDEX
    Explanations

    phrases related to political events and scenarios

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    87
    +0.55
    7.9%
    373
    +0.29
    4.2%
    64
    +0.07
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.55
    -0.00
    373
    +0.29
    -0.14
    756
    +0.07
    -0.09
    Negative Logits
     Quote
    -0.16
     BaseType
    -0.16
     fixme
    -0.16
     sacrific
    -0.15
     mov
    -0.14
     tread
    -0.14
    lite
    -0.14
    )?
    -0.14
     Baal
    -0.13
     Reply
    -0.13
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.17
    å·
    0.17
    ãĥŁ
    0.16
    =~=~
    0.16
    rums
    0.15
    ENTS
    0.15
    ·
    0.15
    é£
    0.14
    romptu
    0.14
    æĢ
    0.14
    Activations Density 6.751%

    No Known Activations