© 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. 10106
    Prev
    Next
    INDEX
    Explanations

    phrases related to political actions and responses

    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
    608
    +0.12
    0.5%
    555
    +0.10
    0.5%
    105
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.12
    0.05
    608
    +0.10
    0.05
    646
    +0.10
    0.04
    Negative Logits
     continuum
    -0.65
     cured
    -0.61
     halves
    -0.59
    agate
    -0.58
     substituted
    -0.57
     ratio
    -0.57
     ppm
    -0.57
     cure
    -0.57
    normal
    -0.57
    arta
    -0.57
    POSITIVE LOGITS
     criticism
    1.15
     applause
    1.13
     ire
    1.07
     scrutiny
    1.07
     controversy
    1.06
     backlash
    1.04
     scorn
    1.02
     outcry
    0.96
     headlines
    0.96
     notoriety
    0.96
    Activations Density 0.199%

    No Known Activations