© 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. 1243
    Prev
    Next
    INDEX
    Explanations

    the suffix "-ud" in names and terms

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names, particularly related to individuals

    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
    xon
    -0.77
    #$
    -0.73
    borough
    -0.61
     diseng
    -0.60
    hazard
    -0.59
     Painter
    -0.58
    Ń·
    -0.58
     combust
    -0.58
    Constructed
    -0.57
     Helsinki
    -0.57
    POSITIVE LOGITS
    geon
    1.44
    geoning
    1.26
    imentary
    1.21
    apest
    1.14
    geons
    1.11
    iamond
    1.03
    ges
    1.03
    olph
    1.02
    gery
    0.96
    gew
    0.95
    Activations Density 0.011%

    No Known Activations