© 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 49152
    9. 8-RES_FS49152-JB
    11. 45754
    Prev
    Next
    INDEX
    Explanations

    statements reflecting personal beliefs about morality and justice in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    640
    +0.11
    0.5%
    232
    +0.10
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.11
    0.07
    232
    +0.10
    0.05
    640
    +0.10
    0.06
    Negative Logits
    ancies
    -0.74
     pri
    -0.65
     departing
    -0.64
     poaching
    -0.62
    ancy
    -0.62
    senal
    -0.60
     originally
    -0.60
    nen
    -0.59
     popping
    -0.59
    ongo
    -0.58
    POSITIVE LOGITS
     Lastly
    1.47
     Finally
    1.41
     And
    1.19
    Lastly
    1.09
    Finally
    1.08
    etc
    1.07
     Whatever
    1.01
     etc
    1.00
     Or
    0.95
     Likewise
    0.95
    Activations Density 0.230%

    No Known Activations