© 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. 4213
    Prev
    Next
    INDEX
    Explanations

    programming code syntax and structure

    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
    137
    +0.13
    0.6%
    441
    +0.11
    0.5%
    337
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    137
    +0.13
    0.02
    441
    +0.11
    0.02
    337
    +0.11
    0.02
    Negative Logits
    agic
    -0.79
    din
    -0.78
    ricular
    -0.77
    rael
    -0.72
    stem
    -0.70
    inators
    -0.68
    riz
    -0.68
    uga
    -0.68
    ensibly
    -0.67
    ays
    -0.66
    POSITIVE LOGITS
     /*
    1.26
     };
    1.23
     }
    1.20
     //
    1.15
     });
    1.02
     ++
    1.00
     /**
    0.96
     ///
    0.95
     @@
    0.90
    };
    0.90
    Activations Density 0.020%

    No Known Activations