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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 14637
    Prev
    Next
    INDEX
    Explanations

    links and calls to action related to supporting and engaging with a specific organization or cause

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words and phrases related to online subscriptions and reader engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ONSORED
    -0.69
    itors
    -0.68
    ursed
    -0.64
    itates
    -0.63
    ITION
    -0.63
    itation
    -0.62
    WARE
    -0.62
    ITED
    -0.62
    ä¸
    -0.62
    itar
    -0.61
    POSITIVE LOGITS
    etting
    0.63
    uyomi
    0.59
    phthal
    0.59
    ilon
    0.58
    pher
    0.57
    eye
    0.55
    ocre
    0.55
    Grade
    0.55
    ierrez
    0.55
    pec
    0.54
    Activations Density 0.269%

    No Known Activations