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 49152
    5. 8-RES_FS49152-JB
    6. 45956
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to ownership or personal relationships

    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
    393
    +0.10
    0.5%
    617
    +0.10
    0.5%
    345
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.05
    345
    +0.10
    0.04
    617
    +0.09
    0.04
    Negative Logits
    eele
    -0.68
     Izan
    -0.64
    ablishment
    -0.63
    arthed
    -0.63
     Unch
    -0.60
     Illum
    -0.60
    vine
    -0.59
    ocument
    -0.58
     Frazier
    -0.57
    river
    -0.57
    POSITIVE LOGITS
     own
    1.55
     OWN
    1.11
    self
    1.11
    selves
    1.03
     Own
    0.98
    elf
    0.93
     rightful
    0.93
     respective
    0.87
     fullest
    0.87
     allotted
    0.85
    Activations Density 0.115%

    No Known Activations