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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 173
    Prev
    Next
    INDEX
    Explanations

    keywords related to a broad range of topics or issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a variety or range of topics or issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hra
    -0.68
    ibling
    -0.67
    ilyn
    -0.66
    fter
    -0.66
     lest
    -0.65
    apo
    -0.63
    riers
    -0.63
    ovember
    -0.63
    ighed
    -0.62
    NN
    -0.61
    POSITIVE LOGITS
     sorts
    1.09
     configurations
    0.93
     styles
    0.92
     viewpoints
    0.90
     different
    0.89
     differing
    0.85
     perspectives
    0.84
     varying
    0.84
     scenarios
    0.84
     possibilities
    0.84
    Activations Density 0.092%

    No Known Activations