© 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. 8-RES-JB
    11. 1183
    Prev
    Next
    INDEX
    Explanations

    mentions related to internet domains and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    specific sequences of letters typically associated with the word "vanguard."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swick
    -0.68
     Takeru
    -0.68
    bender
    -0.65
    ahime
    -0.62
     Betsy
    -0.58
     tc
    -0.58
     Creed
    -0.58
     lest
    -0.56
     Suz
    -0.56
    éĹĺ
    -0.55
    POSITIVE LOGITS
    bilt
    1.03
    unte
    0.83
     versa
    0.79
    emort
    0.79
    ¶æ
    0.78
    namese
    0.76
    atile
    0.76
    ¼
    0.73
    ado
    0.73
    oslav
    0.71
    Activations Density 0.087%

    No Known Activations