© 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. 4-RES-JB
    11. 10637
    Prev
    Next
    INDEX
    Explanations

    words related to guests or individuals attending events

    oai_token-act-pair · gpt-3.5-turbo

    references to attendees or visitors at events

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

    No Comments

    Negative Logits
     Ecology
    -0.62
     systematic
    -0.62
    bin
    -0.60
     taxing
    -0.60
     oxide
    -0.60
    ©¶æ
    -0.60
     Weld
    -0.60
     offsets
    -0.58
     bilateral
    -0.58
     Pac
    -0.54
    POSITIVE LOGITS
    hip
    1.07
     guests
    0.94
     Guests
    0.94
    hips
    0.91
    erv
    0.86
    esses
    0.84
    DragonMagazine
    0.81
    ele
    0.79
    mares
    0.74
     onboard
    0.73
    Activations Density 0.030%

    No Known Activations