© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    political and legislative terms and actions

    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
    +0.27
    1.3%
    447
    +0.18
    0.9%
    745
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.27
    0.08
    288
    +0.18
    0.08
    547
    +0.12
    0.03
    Negative Logits
    )).
    -0.69
    ITNESS
    -0.67
     TOTAL
    -0.64
    OTAL
    -0.62
    oslov
    -0.60
    </
    -0.59
    }}}
    -0.59
    ?".
    -0.59
    idae
    -0.59
    };
    -0.59
    POSITIVE LOGITS
     lately
    0.87
    ourcing
    0.82
     fray
    0.81
     cautiously
    0.78
     bandwagon
    0.76
     eyeing
    0.74
     aggressively
    0.73
     fronts
    0.73
     amid
    0.72
     hoping
    0.72
    Activations Density 0.719%

    No Known Activations