© 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. 26768
    Prev
    Next
    INDEX
    Explanations

    concepts related to authority and expertise in communication

    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
    373
    +0.14
    0.6%
    459
    +0.10
    0.4%
    302
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    482
    +0.14
    0.02
    513
    +0.10
    0.02
    176
    +0.09
    0.02
    Negative Logits
    etimes
    -0.72
     helicop
    -0.68
    Tes
    -0.66
    abolic
    -0.65
     volunte
    -0.64
     glac
    -0.64
     toget
    -0.63
     reluct
    -0.61
    amorph
    -0.61
     indist
    -0.59
    POSITIVE LOGITS
     Explicit
    0.91
    Ability
    0.79
     Clean
    0.76
     Ibid
    0.71
    ï¸ı
    0.70
     Lastly
    0.69
    .—
    0.68
    License
    0.68
    Õ
    0.67
     Flavoring
    0.66
    Activations Density 0.026%

    No Known Activations