© 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. 22437
    Prev
    Next
    INDEX
    Explanations

    nested structures or patterns in data

    oai_token-act-pair · gpt-4o-miniTriggered 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
    314
    +0.10
    0.5%
    160
    +0.10
    0.5%
    289
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.10
    0.02
    289
    +0.10
    0.01
    700
    +0.09
    0.01
    Negative Logits
     predic
    -0.76
     corrid
    -0.74
     reeling
    -0.73
     eaves
    -0.72
     conclud
    -0.72
     antioxid
    -0.72
     labour
    -0.72
     recre
    -0.71
    arios
    -0.70
    vre
    -0.67
    POSITIVE LOGITS
    };
    1.07
    },
    1.03
     Pwr
    1.02
    }{
    0.89
     actionGroup
    0.89
    });
    0.82
    iants
    0.81
    })
    0.80
    flush
    0.79
    âĢ¢âĢ¢
    0.79
    Activations Density 0.010%

    No Known Activations