© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 23070
    Prev
    Next
    INDEX
    Explanations

    technical data points and information related to online activities, such as usernames and activity levels

    oai_token-act-pair · gpt-3.5-turbo

    metrics related to performance or activity levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toile
    -0.71
     irregular
    -0.69
     anten
    -0.67
     unconditional
    -0.63
     Aram
    -0.63
     nep
    -0.63
     rehe
    -0.62
    £ı
    -0.62
     embell
    -0.61
     pollen
    -0.60
    POSITIVE LOGITS
    Thread
    1.06
    Joined
    0.99
    Merit
    0.94
     sidx
    0.89
    姫
    0.83
    BuyableInstoreAndOnline
    0.83
    Location
    0.82
    votes
    0.80
    Posts
    0.80
     Likes
    0.79
    Activations Density 0.044%

    No Known Activations