© 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. 45863
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing mutual support and connection among individuals

    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
    447
    +0.13
    0.6%
    125
    +0.12
    0.5%
    592
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    125
    +0.13
    0.01
    225
    +0.12
    0.01
    528
    +0.11
    0.01
    Negative Logits
    uci
    -0.78
    0002
    -0.70
    lam
    -0.64
    hift
    -0.63
     reimb
    -0.63
    ariat
    -0.61
    °
    -0.61
    alty
    -0.60
    nit
    -0.60
     DK
    -0.60
    POSITIVE LOGITS
    selves
    0.92
    worldly
    0.83
     individually
    0.80
    self
    0.74
     equally
    0.71
    heric
    0.70
     offensively
    0.68
    é¾įåĸļ士
    0.68
    anguages
    0.68
     mutually
    0.67
    Activations Density 0.009%

    No Known Activations