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 3072
    5. 8-RES_FS3072-JB
    6. 1841
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations or specific events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    195
    +0.18
    0.8%
    420
    +0.13
    0.6%
    459
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.18
    0.05
    18
    +0.13
    0.05
    232
    +0.11
    0.05
    Negative Logits
    ruciating
    -0.85
    ¥ŀ
    -0.77
    è¦ļéĨĴ
    -0.72
    ¥µ
    -0.70
     stakes
    -0.66
     Thumbnails
    -0.61
     ABE
    -0.59
     Hour
    -0.57
    ished
    -0.57
     boy
    -0.56
    POSITIVE LOGITS
    abeth
    1.12
    olation
    1.08
    olate
    1.05
    terness
    1.00
    creen
    0.93
    rael
    0.91
    cience
    0.89
    abis
    0.88
    ystem
    0.86
    elman
    0.85
    Activations Density 0.730%

    No Known Activations