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. 10304
    Prev
    Next
    INDEX
    Explanations

    options or settings within a software interface

    oai_token-act-pair · gpt-3.5-turbo

    references to options and settings in software configurations

    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
    conom
    -0.83
    lik
    -0.82
    waters
    -0.80
     resil
    -0.74
    llah
    -0.70
    isky
    -0.70
    ocamp
    -0.69
    photos
    -0.68
     bos
    -0.68
    cling
    -0.68
    POSITIVE LOGITS
    erred
    0.81
     Filter
    0.76
     override
    0.76
     explicitly
    0.75
    Override
    0.75
     overr
    0.75
     "-
    0.72
     popup
    0.72
     Enable
    0.71
     headers
    0.70
    Activations Density 0.083%

    No Known Activations