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 3072
    5. 8-RES_FS3072-JB
    6. 1723
    Prev
    Next
    INDEX
    Explanations

    words related to technology and software

    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
    218
    +0.10
    0.4%
    709
    +0.09
    0.4%
    302
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    718
    +0.10
    0.08
    490
    +0.09
    0.06
    389
    +0.09
    0.05
    Negative Logits
     Impossible
    -0.69
    ĨĴ
    -0.68
    ocr
    -0.67
    Offline
    -0.65
    thood
    -0.64
    Ó
    -0.63
    wich
    -0.62
    onential
    -0.61
    idel
    -0.61
    ories
    -0.61
    POSITIVE LOGITS
    hin
    0.72
     temptation
    0.71
    ECK
    0.65
     gorgeous
    0.61
    RAG
    0.61
    amaz
    0.61
    XM
    0.60
    MpServer
    0.60
    âĶĢ
    0.59
     Schne
    0.58
    Activations Density 1.737%

    No Known Activations