© 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. 10-RES-JB
    11. 18749
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to game development and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sbm
    -0.80
     Cosponsors
    -0.69
    ovember
    -0.68
    emort
    -0.67
    DragonMagazine
    -0.62
    uctions
    -0.61
    uala
    -0.61
    qqa
    -0.60
    ydia
    -0.60
    pread
    -0.60
    POSITIVE LOGITS
     thereof
    0.64
     oneself
    0.59
     OF
    0.52
     theirs
    0.51
     Colombian
    0.50
     his
    0.47
     itself
    0.47
     Spanish
    0.47
     own
    0.46
     Of
    0.46
    Activations Density 0.593%

    No Known Activations