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

    Neuronpedia

    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. 7473
    Prev
    Next
    INDEX
    Explanations

    shortened URLs typically associated with stories or links to be shared

    oai_token-act-pair · gpt-3.5-turbo

    URLs and web-related content

    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
    PAC
    -0.61
    rators
    -0.60
     Alexandria
    -0.59
     Gott
    -0.58
    ©¶æ
    -0.56
    Same
    -0.56
     Kut
    -0.55
     Aires
    -0.54
    rals
    -0.53
    anus
    -0.53
    POSITIVE LOGITS
    Thumbnail
    0.71
    legraph
    0.71
    yssey
    0.68
    pmwiki
    0.68
    img
    0.65
    cdn
    0.64
    pn
    0.64
    biz
    0.63
    rc
    0.61
     bearer
    0.61
    Activations Density 0.033%

    No Known Activations