© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 49152
    5. 8-RES_FS49152-JB
    6. 45462
    Prev
    Next
    INDEX
    Explanations

    terms related to disappointment and decline

    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
    87
    +0.33
    1.7%
    298
    +0.09
    0.5%
    756
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.33
    -0.01
    737
    +0.09
    0.04
    298
    +0.08
    0.04
    Negative Logits
    aeper
    -0.61
     pione
    -0.60
     TheNitrome
    -0.59
    ù
    -0.58
    ö
    -0.58
    ė
    -0.58
    Ą
    -0.58
    ü
    -0.58
     practition
    -0.58
    Á
    -0.58
    POSITIVE LOGITS
    luster
    0.60
    wards
    0.59
    rils
    0.59
     amid
    0.58
     roses
    0.57
     prevail
    0.56
     until
    0.55
     clouds
    0.55
    blown
    0.55
    .
    0.55
    Activations Density 0.380%

    No Known Activations