© 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 EvalsExportsinterp-engineNEWAPI 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. 2767
    Prev
    Next
    INDEX
    Explanations

    topics related to politics, current events, and societal issues

    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
    481
    +0.24
    1.1%
    475
    +0.09
    0.4%
    254
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.24
    0.07
    475
    +0.09
    0.05
    325
    +0.09
    0.05
    Negative Logits
     guiName
    -0.76
     mathemat
    -0.65
    olulu
    -0.58
     defic
    -0.58
     Amen
    -0.55
    CONCLUS
    -0.54
     Horus
    -0.52
    Anth
    -0.52
     '/
    -0.52
    ensional
    -0.52
    POSITIVE LOGITS
    )—
    1.75
    )?
    1.47
    )
    1.45
    )--
    1.44
    *)
    1.41
    ),
    1.39
    )}
    1.35
    !),
    1.34
    ?),
    1.30
    !)
    1.28
    Activations Density 0.632%

    No Known Activations