© 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. 9-RES-JB
    11. 15960
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and."

    oai_token-act-pair · gpt-3.5-turbo

    instances of special characters or formatting in the text

    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
    bub
    -0.59
    Leaks
    -0.52
    egu
    -0.51
    hub
    -0.51
    .*
    -0.51
    seat
    -0.51
    hoe
    -0.50
     recogn
    -0.48
     foul
    -0.47
    —-
    -0.47
    POSITIVE LOGITS
    romeda
    0.99
    rogens
    0.99
    rew
    0.96
    ERSON
    0.94
    rogen
    0.87
    then
    0.71
    rost
    0.71
    alus
    0.69
    rea
    0.67
     secondly
    0.67
    Activations Density 0.063%

    No Known Activations