© 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. 7666
    Prev
    Next
    INDEX
    Explanations

    titles or mentions of people's names

    oai_token-act-pair · gpt-3.5-turbo

    specific punctuation or separators in text, primarily periods

    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
     advis
    -0.83
     applicable
    -0.71
     confidentiality
    -0.68
    olation
    -0.67
     heels
    -0.66
    metadata
    -0.65
    onies
    -0.65
    itives
    -0.62
     chopping
    -0.62
    edly
    -0.61
    POSITIVE LOGITS
    J
    1.34
    Va
    1.17
    O
    1.14
    A
    1.12
    C
    1.12
    E
    1.12
    L
    1.10
    P
    1.10
    M
    1.09
    R
    1.09
    Activations Density 0.042%

    No Known Activations