© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 20143
    Prev
    Next
    INDEX
    Explanations

    words related to signing up or adding someone to a roster or agreement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "signing."

    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
    gypt
    -0.82
    aceae
    -0.67
    angles
    -0.62
    Guide
    -0.62
    Loop
    -0.60
    Parts
    -0.60
    mares
    -0.60
     Investigations
    -0.59
    surv
    -0.58
    cam
    -0.58
    POSITIVE LOGITS
     signing
    3.95
     signings
    2.47
     signed
    2.00
    signed
    1.74
     sign
    1.74
    sign
    1.65
     Sign
    1.61
     Signed
    1.56
     drafting
    1.47
     agreeing
    1.36
    Activations Density 0.009%

    No Known Activations