© 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. 0-RES-JB
    11. 15715
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames, specifically those related to SB

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the abbreviation "SB" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     excav
    -0.70
     moder
    -0.65
     ferment
    -0.64
     engagements
    -0.63
     Et
    -0.63
     elephant
    -0.63
     Oxy
    -0.60
     explorer
    -0.59
     sit
    -0.59
     engagement
    -0.59
    POSITIVE LOGITS
    SB
    4.58
     SB
    1.71
    HB
    1.56
    SF
    1.54
    sb
    1.41
    SO
    1.36
    SL
    1.35
    SK
    1.33
    PB
    1.30
    TB
    1.27
    Activations Density 0.011%

    No Known Activations