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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 319
    Prev
    Next
    INDEX
    Explanations

    definitions and explanations of technical terms

    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
    447
    +0.29
    1.6%
    373
    +0.24
    1.3%
    478
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.29
    -0.10
    460
    +0.24
    0.04
    326
    +0.09
    0.13
    Negative Logits
    ranch
    -0.50
     POLITICO
    -0.48
     bloc
    -0.45
    iq
    -0.44
    oting
    -0.43
     parity
    -0.42
     corpor
    -0.42
     automation
    -0.41
    inance
    -0.41
     cov
    -0.41
    POSITIVE LOGITS
     Amen
    0.70
    .''.
    0.63
     =================================================================
    0.62
    )."
    0.60
    }}}
    0.59
    åħī
    0.59
    !".
    0.59
    CONCLUS
    0.59
     Lastly
    0.58
    --------------------------------
    0.58
    Activations Density 2.834%

    No Known Activations