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. 9503
    Prev
    Next
    INDEX
    Explanations

    mentions of medical terms and conditions such as "systolic", "anxious", and "polyurethane" in the text

    oai_token-act-pair · gpt-3.5-turbo

    combinations of letters suggesting scientific or medical terminology

    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
     largeDownload
    -0.70
    tsky
    -0.69
     Dull
    -0.69
    ĸļ
    -0.66
    yip
    -0.65
     Bagg
    -0.64
    jriwal
    -0.60
    ecause
    -0.60
     Sparks
    -0.60
    ammy
    -0.60
    POSITIVE LOGITS
    ologically
    0.81
    hetic
    0.78
    orous
    0.77
    ical
    0.76
    mal
    0.76
    arian
    0.73
    arine
    0.72
    arious
    0.71
    allic
    0.71
    omedical
    0.70
    Activations Density 0.113%

    No Known Activations