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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9357
    Prev
    Next
    INDEX
    Explanations

    information related to signing up for newsletters or updates

    oai_token-act-pair · gpt-3.5-turbo

    sign-up prompts and calls to action related to newsletters or subscriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lite
    -0.68
    TABLE
    -0.67
     unaccount
    -0.65
     bragging
    -0.64
    sed
    -0.64
    ELY
    -0.63
    BALL
    -0.62
    WHERE
    -0.61
    tf
    -0.59
    naire
    -0.58
    POSITIVE LOGITS
    DragonMagazine
    0.63
     passports
    0.62
     Maze
    0.61
    merga
    0.61
     Vulkan
    0.60
     UAE
    0.60
    ija
    0.60
     metre
    0.60
    ulkan
    0.59
     Sign
    0.59
    Activations Density 0.058%

    No Known Activations