© 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. 41484
    Prev
    Next
    INDEX
    Explanations

    negative implications or critiques regarding social and political issues

    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
    675
    +0.12
    0.6%
    314
    +0.12
    0.5%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.12
    0.08
    48
    +0.12
    0.05
    504
    +0.11
    0.05
    Negative Logits
     ende
    -0.75
     scattering
    -0.72
     myster
    -0.69
    seless
    -0.68
     seiz
    -0.65
     federation
    -0.64
     proport
    -0.64
     encount
    -0.63
     obser
    -0.63
     notor
    -0.63
    POSITIVE LOGITS
    ï¸ı
    0.96
    ¯
    0.91
    #$
    0.79
    °
    0.79
    Tea
    0.73
    ef
    0.72
    âĢł
    0.72
    dj
    0.70
    cue
    0.68
    hips
    0.68
    Activations Density 0.120%

    No Known Activations