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 6144
    5. 8-RES_FS6144-JB
    6. 5459
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods specifically referring to the 21st century

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs6144-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    6,144
    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
    276
    +0.15
    0.7%
    377
    +0.14
    0.7%
    223
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.15
    0.06
    693
    +0.14
    0.05
    310
    +0.12
    0.05
    Negative Logits
     externalToEVAOnly
    -0.90
    ulously
    -0.74
    ensional
    -0.72
     Polo
    -0.71
    riages
    -0.71
    tered
    -0.68
     plain
    -0.66
    akespe
    -0.65
    atics
    -0.65
    orah
    -0.65
    POSITIVE LOGITS
    st
    1.44
    nect
    0.92
    ĪĴ
    0.81
    ST
    0.81
    naire
    0.75
    onsense
    0.74
    entimes
    0.72
    worthy
    0.70
    WI
    0.69
    ãĤĮ
    0.69
    Activations Density 0.444%

    No Known Activations