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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12177
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to demographic and social statistics

    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
    447
    +0.14
    0.6%
    5
    +0.10
    0.4%
    648
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    51
    +0.14
    0.03
    288
    +0.10
    0.04
    1
    +0.10
    0.03
    Negative Logits
    cffffcc
    -0.93
    ãĤ´ãĥ³
    -0.82
    çīĪ
    -0.69
    ĪĴ
    -0.68
     guise
    -0.66
    eln
    -0.65
    ĺħ
    -0.63
    eatures
    -0.62
    arton
    -0.61
     sensibilities
    -0.60
    POSITIVE LOGITS
     per
    0.93
     available
    0.84
     consumed
    0.80
     involved
    0.79
     allocated
    0.78
     counted
    0.78
     surveyed
    0.76
     devoted
    0.75
     needed
    0.75
     polled
    0.74
    Activations Density 0.162%

    No Known Activations