© 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. 37576
    Prev
    Next
    INDEX
    Explanations

    words related to negative attributes or descriptions

    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
    362
    +0.12
    0.6%
    91
    +0.12
    0.6%
    446
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.12
    0.06
    91
    +0.12
    0.05
    408
    +0.12
    0.06
    Negative Logits
    uther
    -0.91
    uph
    -0.85
    redits
    -0.81
    vier
    -0.78
    ecause
    -0.77
    available
    -0.74
    --------------------
    -0.73
    Gi
    -0.73
    soType
    -0.73
    icter
    -0.72
    POSITIVE LOGITS
     counterparts
    1.31
     namesake
    1.21
     counterpart
    1.17
     predecessors
    1.17
     reputation
    1.14
     cousin
    1.14
     predecessor
    1.13
     brethren
    1.10
     fortunes
    1.08
     surroundings
    1.07
    Activations Density 0.183%

    No Known Activations