© 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. 45735
    Prev
    Next
    INDEX
    Explanations

    phrases indicating participation or involvement in activities or agreements

    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
    447
    +0.13
    0.6%
    218
    +0.13
    0.6%
    560
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.13
    0.02
    307
    +0.13
    0.01
    210
    +0.10
    0.01
    Negative Logits
    usercontent
    -0.69
    asca
    -0.63
     benches
    -0.63
     mov
    -0.63
     drowned
    -0.62
     ankles
    -0.60
     pots
    -0.59
     creeps
    -0.59
    istors
    -0.57
     pores
    -0.56
    POSITIVE LOGITS
     meantime
    0.80
     precaution
    0.74
     clarification
    0.66
     commem
    0.63
    compliance
    0.62
     disclaim
    0.61
    gencies
    0.61
    FAQ
    0.60
    ward
    0.59
    claimer
    0.59
    Activations Density 0.033%

    No Known Activations