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. 5432
    Prev
    Next
    INDEX
    Explanations

    information related to news articles, reports, and legal documents

    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
    767
    +0.12
    0.5%
    513
    +0.10
    0.4%
    515
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.12
    0.05
    530
    +0.10
    0.04
    373
    +0.10
    -0.02
    Negative Logits
    igrate
    -0.69
    ophobic
    -0.69
    avour
    -0.67
    vs
    -0.67
    raq
    -0.67
     haunt
    -0.67
    geist
    -0.66
    aston
    -0.66
    rower
    -0.66
    erson
    -0.65
    POSITIVE LOGITS
    license
    0.92
     permission
    0.82
     copyright
    0.79
    alysed
    0.76
    çīĪ
    0.74
     License
    0.73
     licensed
    0.72
     license
    0.71
     copyrighted
    0.71
     trademark
    0.71
    Activations Density 0.390%

    No Known Activations