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. 23698
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that express a lack of confidence or uncertainty surrounding a situation

    oai_token-act-pair · gpt-4o-miniTriggered 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
    373
    +0.13
    0.6%
    762
    +0.11
    0.5%
    15
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.13
    0.03
    437
    +0.11
    0.02
    331
    +0.10
    0.03
    Negative Logits
     Flavoring
    -0.74
    kefeller
    -0.63
    éŃĶ
    -0.63
    Merit
    -0.60
    ickets
    -0.59
    osate
    -0.56
    advertising
    -0.55
     OPEC
    -0.55
     Cosponsors
    -0.54
     Reboot
    -0.54
    POSITIVE LOGITS
    !?
    0.78
    ????????
    0.75
    ?!
    0.71
    ????
    0.70
    ???
    0.67
    ...?
    0.64
     huh
    0.64
    course
    0.60
    âĶĢâĶĢâĶĢâĶĢ
    0.60
    "?
    0.59
    Activations Density 0.564%

    No Known Activations