© 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 24576
    9. 8-RES_FS24576-JB
    11. 19546
    Prev
    Next
    INDEX
    Explanations

    comparisons between different quantities, emphasizing increases or decreases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    373
    +0.14
    0.6%
    726
    +0.13
    0.6%
    19
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    726
    +0.14
    0.03
    647
    +0.13
    0.02
    190
    +0.09
    0.02
    Negative Logits
    æ©
    -0.79
    borg
    -0.71
    boxing
    -0.71
    xtap
    -0.67
     Outbreak
    -0.67
     Classification
    -0.66
    Ń·
    -0.64
    \\\\\\\\
    -0.63
    atan
    -0.63
    ����
    -0.63
    POSITIVE LOGITS
     than
    0.79
     fortunate
    0.79
     desirable
    0.79
     mature
    0.79
     prevalent
    0.78
     importantly
    0.78
     realistic
    0.78
     inclined
    0.75
     frequent
    0.74
     adventurous
    0.74
    Activations Density 0.020%

    No Known Activations