© 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 EvalsExportsAPI 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. 7-RES-JB
    11. 1895
    Prev
    Next
    INDEX
    Explanations

    statements or inquiries prompting reflection or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "U" followed by a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utterstock
    -0.71
     disse
    -0.68
     basics
    -0.66
    ãĤ©
    -0.62
    ãĤ¨ãĥ«
    -0.61
     browsing
    -0.61
    olis
    -0.61
     srfAttach
    -0.60
    ãĥ¼ãĥĨãĤ£
    -0.59
    redients
    -0.59
    POSITIVE LOGITS
    S
    0.86
     Soccer
    0.80
    $.
    0.76
     Geological
    0.73
    Va
    0.73
    N
    0.70
     Embassy
    0.70
     Nations
    0.70
     Pact
    0.67
    government
    0.67
    Activations Density 0.049%

    No Known Activations