© 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 24576
    9. 8-RES_FS24576-JB
    11. 7101
    Prev
    Next
    INDEX
    Explanations

    code-related instructions and programming 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_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
    +0.16
    0.7%
    756
    +0.12
    0.6%
    506
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.16
    0.03
    176
    +0.12
    0.02
    570
    +0.11
    0.01
    Negative Logits
    oat
    -0.67
    omething
    -0.66
    offensive
    -0.60
    cit
    -0.60
    egal
    -0.59
    tin
    -0.59
    osc
    -0.59
    fam
    -0.59
    asia
    -0.59
    bi
    -0.58
    POSITIVE LOGITS
     };
    1.39
     });
    1.17
    };
    1.13
     }
    1.10
     </
    1.05
     /*
    1.00
     }}
    0.97
     ];
    0.96
     //
    0.95
     ********************************
    0.94
    Activations Density 0.067%

    No Known Activations