© 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. 4-RES-JB
    11. 16779
    Prev
    Next
    INDEX
    Explanations

    words related to urgent situations or emergencies

    oai_token-act-pair · gpt-3.5-turbo

    specific structured data or information formatted in a list or numbered outline

    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
    ichick
    -0.78
    uggest
    -0.72
    iden
    -0.65
    ittal
    -0.64
    hens
    -0.64
     refres
    -0.64
    ivable
    -0.63
    ollow
    -0.63
    ards
    -0.63
    onomous
    -0.62
    POSITIVE LOGITS
    HEAD
    1.14
    WORK
    1.14
    HAM
    1.12
    MENT
    1.12
    LET
    1.08
     SCHOOL
    1.04
     EDITION
    1.03
     HOL
    1.01
    URA
    1.01
    TOP
    1.01
    Activations Density 0.268%

    No Known Activations