© 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 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. 10147
    Prev
    Next
    INDEX
    Explanations

    phrases related to political controversy

    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
    +0.13
    0.6%
    135
    +0.12
    0.5%
    255
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    221
    +0.13
    0.04
    176
    +0.12
    0.03
    762
    +0.12
    0.05
    Negative Logits
    76561
    -0.72
     sponsoring
    -0.60
    WithNo
    -0.58
     hurd
    -0.57
     newcom
    -0.56
    naissance
    -0.56
     repertoire
    -0.54
    icho
    -0.53
    bryce
    -0.52
    ãĥ«
    -0.51
    POSITIVE LOGITS
    ;
    0.96
    .
    0.87
    ?,
    0.81
    .—
    0.80
    !,
    0.78
    ;}
    0.77
    !
    0.74
     depending
    0.73
    .--
    0.72
     —
    0.72
    Activations Density 0.488%

    No Known Activations