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. 3-RES-JB
    6. 19762
    Prev
    Next
    INDEX
    Explanations

    queries or statements related to database operations based on certain conditions

    oai_token-act-pair · gpt-3.5-turbo

    queries related to persons and their attributes, particularly age

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.93
    etheless
    -0.89
    wcs
    -0.62
    minist
    -0.62
     showc
    -0.59
    answered
    -0.56
    ————————
    -0.55
    BILITIES
    -0.55
    gencies
    -0.55
    ":[{"
    -0.55
    POSITIVE LOGITS
    )."
    1.71
    )"
    1.65
    )
    1.65
    ?)
    1.64
    !)
    1.62
    ),"
    1.61
    ).
    1.55
    )}
    1.54
    ?).
    1.53
    )|
    1.53
    Activations Density 1.283%

    No Known Activations