© 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. 0-RES-JB
    11. 19280
    Prev
    Next
    INDEX
    Explanations

    names containing the pattern "Humph" or "Wim"

    oai_token-act-pair · gpt-3.5-turbo

    names related to individuals with the surname "Humphrey" and terms associated with specific groups or organizations

    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
    load
    -0.78
     âĸº
    -0.74
     Toro
    -0.73
     Lilith
    -0.71
    ESE
    -0.70
    wrapper
    -0.70
     Loot
    -0.69
    aco
    -0.68
    selage
    -0.68
    LOAD
    -0.68
    POSITIVE LOGITS
     Humph
    3.39
     Wor
    1.55
     Berman
    1.33
     Wim
    1.28
    umph
    1.16
    ownt
    1.12
     racket
    1.11
     Dup
    1.09
     Fav
    1.04
     Hed
    1.01
    Activations Density 0.050%

    No Known Activations