Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 966
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    242
    +0.12
    0.5%
    354
    +0.11
    0.5%
    603
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.12
    0.02
    601
    +0.11
    0.02
    354
    +0.10
    0.03
    Negative Logits
     sugg
    -0.78
    ikk
    -0.66
    inqu
    -0.61
    adish
    -0.61
    ksh
    -0.60
    VEN
    -0.59
     Inqu
    -0.59
     venture
    -0.59
    ule
    -0.58
    isure
    -0.56
    POSITIVE LOGITS
    png
    0.83
     signs
    0.75
     resemblance
    0.74
     versatility
    0.72
     plainly
    0.72
     glimps
    0.72
    ibilities
    0.72
     naked
    0.70
     clearly
    0.70
    formance
    0.70
    Activations Density 0.138%

    No Known Activations