© 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. 3-RES-JB
    11. 165
    Prev
    Next
    INDEX
    Explanations

    dates and structured text patterns

    oai_token-act-pair · gpt-3.5-turbo

    references to specific routes and scheduling information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendars
    -0.73
    20439
    -0.62
     SIGN
    -0.54
    pres
    -0.54
    gm
    -0.54
     favor
    -0.54
     ranc
    -0.52
    SIGN
    -0.52
    kl
    -0.51
     corpor
    -0.50
    POSITIVE LOGITS
    escription
    0.86
    senal
    0.79
    cember
    0.70
    dinand
    0.68
     Azerb
    0.66
    ucer
    0.66
    uces
    0.64
    intosh
    0.64
     ItemLevel
    0.63
    icut
    0.63
    Activations Density 0.766%

    No Known Activations