© 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. 45838
    Prev
    Next
    INDEX
    Explanations

    references to friendship and companionship

    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
    247
    +0.15
    0.7%
    51
    +0.10
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    247
    +0.15
    0.02
    506
    +0.10
    0.02
    377
    +0.10
    0.02
    Negative Logits
    senal
    -0.73
     millenn
    -0.72
     chloride
    -0.69
     Cout
    -0.64
    ilion
    -0.63
    teen
    -0.61
     untreated
    -0.61
    nsic
    -0.61
    elsius
    -0.60
    etheus
    -0.60
    POSITIVE LOGITS
    liest
    1.68
    liness
    1.66
    lier
    1.46
    lies
    1.41
    ship
    1.21
    ships
    1.20
    finder
    0.90
    strom
    0.82
    hips
    0.81
    friend
    0.80
    Activations Density 0.023%

    No Known Activations