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. 11948
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical objects and their components

    oai_token-act-pair · gpt-3.5-turbo

    details related to components and packaging of a game or product

    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
    heimer
    -0.64
    nesty
    -0.64
    arians
    -0.59
     criminal
    -0.58
     terrorism
    -0.57
    osate
    -0.56
    endon
    -0.54
    Leary
    -0.54
    AFP
    -0.54
     jeopard
    -0.53
    POSITIVE LOGITS
     rectangular
    0.87
     collaps
    0.83
     diagrams
    0.79
     folders
    0.78
     interchangeable
    0.75
     translucent
    0.73
     divid
    0.72
     removable
    0.71
     optionally
    0.71
     modular
    0.70
    Activations Density 1.654%

    No Known Activations