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. 1-RES-JB
    6. 24528
    Prev
    Next
    INDEX
    Explanations

    references to specific car racing teams or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or entities in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     allerg
    -0.78
     bottled
    -0.67
     moratorium
    -0.65
     tob
    -0.65
     preached
    -0.62
    icator
    -0.62
     pestic
    -0.62
    packages
    -0.61
    ©¶æ
    -0.61
     comr
    -0.61
    POSITIVE LOGITS
    Shape
    0.73
    ename
    0.67
    ysis
    0.66
     Rouge
    0.66
    zag
    0.64
     Massive
    0.64
    furt
    0.63
    mom
    0.61
    kid
    0.61
    tale
    0.61
    Activations Density 0.000%

    No Known Activations