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. 18982
    Prev
    Next
    INDEX
    Explanations

    texts related to analyzing and discussing various topics such as articles, reports, courses, history, advice, and more

    oai_token-act-pair · gpt-3.5-turbo

    evaluations and analyses of academic articles or studies

    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
     Izan
    -0.74
    人
    -0.69
    76561
    -0.64
     Presumably
    -0.62
    alled
    -0.62
    answered
    -0.59
    izu
    -0.59
    ['
    -0.58
     mentioned
    -0.57
    umably
    -0.57
    POSITIVE LOGITS
     curated
    0.78
     explores
    0.77
     versatile
    0.75
     innovative
    0.74
     immersive
    0.71
     showcases
    0.70
     explore
    0.66
     satirical
    0.65
     interactive
    0.65
     unparalleled
    0.65
    Activations Density 1.320%

    No Known Activations