© 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. 11-RES-JB
    11. 7804
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    oai_token-act-pair · gpt-3.5-turbo

    references to red-top headlines or sensationalist media structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tiny
    -0.83
     Tall
    -0.80
     Bull
    -0.78
     Helic
    -0.77
     Mystic
    -0.75
     Dynam
    -0.74
     Carnegie
    -0.74
     Tab
    -0.73
     Syl
    -0.73
     Virtual
    -0.72
    POSITIVE LOGITS
    based
    1.41
    level
    1.34
    enough
    1.33
    bearing
    1.32
    bodied
    1.31
    direction
    1.29
    related
    1.29
    deal
    1.28
    only
    1.28
    group
    1.28
    Activations Density 0.139%

    No Known Activations