© 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 49152
    9. 8-RES_FS49152-JB
    11. 45565
    Prev
    Next
    INDEX
    Explanations

    words related to authority and dissent in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    430
    +0.11
    0.5%
    556
    +0.10
    0.5%
    746
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    556
    +0.11
    0.02
    232
    +0.10
    0.02
    111
    +0.10
    0.01
    Negative Logits
    anwhile
    -0.69
    utical
    -0.69
     lapse
    -0.66
    doms
    -0.65
    afety
    -0.64
     parcels
    -0.64
     ripe
    -0.62
    iguous
    -0.62
    hern
    -0.61
    sylv
    -0.61
    POSITIVE LOGITS
    issance
    1.02
    wagen
    0.71
     Wagner
    0.69
    izzle
    0.69
    spective
    0.68
    invoke
    0.68
     Cathedral
    0.67
    ctive
    0.67
     Rollins
    0.66
    enment
    0.66
    Activations Density 0.063%

    No Known Activations