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. 26348
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate presence or location

    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
    314
    +0.13
    0.6%
    373
    +0.11
    0.5%
    196
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.13
    0.02
    22
    +0.11
    0.02
    616
    +0.09
    0.01
    Negative Logits
     unemploy
    -0.67
     guiActiveUn
    -0.67
    ãģ®å®
    -0.63
     pse
    -0.61
    BIL
    -0.59
     juggling
    -0.57
    Ĥİ
    -0.57
    sted
    -0.57
    frog
    -0.57
    Attempts
    -0.57
    POSITIVE LOGITS
    eff
    0.72
    arius
    0.71
    itant
    0.70
    irin
    0.68
     essence
    0.66
    actly
    0.66
     parentheses
    0.65
    gest
    0.62
    arg
    0.62
    pled
    0.61
    Activations Density 0.037%

    No Known Activations