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. 26456
    Prev
    Next
    INDEX
    Explanations

    expressions related to offering assistance or support

    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
    327
    +0.10
    0.4%
    718
    +0.10
    0.4%
    508
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.10
    0.04
    327
    +0.10
    0.04
    108
    +0.09
    0.03
    Negative Logits
    theless
    -0.80
    rencies
    -0.71
    iu
    -0.69
    ross
    -0.66
    irus
    -0.65
    Pict
    -0.65
    pora
    -0.63
    Compar
    -0.63
    alled
    -0.63
    NB
    -0.62
    POSITIVE LOGITS
     facilitate
    0.88
     alleviate
    0.87
     organize
    0.86
     him
    0.85
     educate
    0.85
    meet
    0.84
     organise
    0.83
     needy
    0.83
    fully
    0.83
     them
    0.80
    Activations Density 0.044%

    No Known Activations