© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10223
    Prev
    Next
    INDEX
    Explanations

    names and terms with unusual characters like 'âĢĻ'

    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
    480
    +0.32
    1.6%
    87
    +0.14
    0.7%
    314
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.32
    0.11
    720
    +0.14
    0.10
    584
    +0.14
    0.10
    Negative Logits
     mathemat
    -0.84
     incorpor
    -0.83
     disadvant
    -0.79
     fortun
    -0.78
     lawy
    -0.77
     Palestin
    -0.76
     unden
    -0.72
     predec
    -0.70
     obser
    -0.69
     notor
    -0.68
    POSITIVE LOGITS
    ï¸ı
    1.58
    âĶĢâĶĢâĶĢâĶĢ
    0.93
    âĶĢâĶĢ
    0.93
    âĻ
    0.92
    ï¸
    0.90
    £
    0.90
    §
    0.82
    iversary
    0.80
    ··
    0.80
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    0.79
    Activations Density 0.265%

    No Known Activations