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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1745
    Prev
    Next
    INDEX
    Explanations

    proper nouns and titles of publications

    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
    659
    +0.14
    0.6%
    336
    +0.12
    0.5%
    364
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.09
    364
    +0.12
    0.06
    336
    +0.10
    0.06
    Negative Logits
     Vaj
    -0.66
     Cerberus
    -0.65
     upside
    -0.64
     unsupported
    -0.63
     surve
    -0.60
     Sparrow
    -0.60
     hypot
    -0.59
    espie
    -0.59
     slack
    -0.57
     inund
    -0.56
    POSITIVE LOGITS
    onsense
    1.32
    uggets
    1.27
    ucle
    1.25
    umerous
    1.24
    aughty
    1.21
    ihil
    1.19
    autical
    1.17
    umeric
    1.16
    guyen
    1.15
    erves
    1.12
    Activations Density 0.326%

    No Known Activations