© 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 12288
    9. 8-RES_FS12288-JB
    11. 10777
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and criminal activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    +0.56
    3.1%
    266
    +0.16
    0.9%
    87
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.56
    0.04
    266
    +0.16
    0.14
    603
    +0.12
    0.06
    Negative Logits
    .",
    -0.61
    Medium
    -0.60
    .:
    -0.56
    %.
    -0.53
    izoph
    -0.53
    ":[
    -0.53
     conclud
    -0.52
    unless
    -0.50
    rition
    -0.49
    OTAL
    -0.49
    POSITIVE LOGITS
     )]
    0.89
    *)
    0.86
    )]
    0.82
    )?
    0.79
    })
    0.76
    )}
    0.76
     ?)
    0.71
    )|
    0.71
    )\
    0.71
    ?)
    0.71
    Activations Density 2.563%

    No Known Activations