© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 37350
    Prev
    Next
    INDEX
    Explanations

    suffixes related to adjectives and adverbs

    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
    273
    +0.10
    0.5%
    616
    +0.09
    0.4%
    430
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    622
    +0.10
    0.01
    435
    +0.09
    0.01
    284
    +0.09
    0.01
    Negative Logits
    isSpecialOrderable
    -0.69
    luster
    -0.66
     invol
    -0.64
    matically
    -0.64
     recru
    -0.64
    kefeller
    -0.61
    floor
    -0.61
    alian
    -0.59
    è¦ļéĨĴ
    -0.59
     machine
    -0.59
    POSITIVE LOGITS
    iability
    0.80
    iably
    0.75
    éĸ
    0.75
     Marin
    0.69
    iable
    0.68
    chuk
    0.67
    iox
    0.66
    ignty
    0.65
    ia
    0.64
    ias
    0.64
    Activations Density 0.022%

    No Known Activations