© 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. 24431
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names, possibly titles or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letters "Ch" and certain character sequences

    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
     dial
    -0.89
     OD
    -0.78
     Pell
    -0.73
     Roll
    -0.73
     Frie
    -0.72
    OOL
    -0.71
     Ern
    -0.70
     rolled
    -0.70
    éĸ
    -0.69
     roll
    -0.69
    POSITIVE LOGITS
    as
    1.68
    AS
    1.61
    asus
    1.37
    kas
    1.34
    ases
    1.31
    asu
    1.29
    asse
    1.28
    asa
    1.28
    asin
    1.25
    asm
    1.18
    Activations Density 0.165%

    No Known Activations