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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 643
    Prev
    Next
    INDEX
    Explanations

    keywords related to inventory and supplies

    oai_token-act-pair · gpt-3.5-turbo

    references to inventory or availability of items

    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
    BLE
    -0.81
    mes
    -0.76
    undai
    -0.73
    inx
    -0.72
    soever
    -0.71
    ptoms
    -0.68
    ROR
    -0.68
    icz
    -0.68
    selves
    -0.66
    mable
    -0.64
    POSITIVE LOGITS
    holders
    1.25
    holder
    1.06
    holm
    0.95
    yards
    0.92
    ings
    0.83
    still
    0.80
    dale
    0.73
    ivities
    0.73
    ickers
    0.72
    picking
    0.72
    Activations Density 0.011%

    No Known Activations