© 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 EvalsExportsinterp-engineNEWAPI 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. 20998
    Prev
    Next
    INDEX
    Explanations

    information related to reasoning and argumentation

    oai_token-act-pair · gpt-3.5-turbo

    significant numerical values or statistics related to critical issues

    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
    Custom
    -0.64
     Instr
    -0.63
     handshake
    -0.63
     "+
    -0.63
     \"
    -0.63
     Likes
    -0.62
     swearing
    -0.61
     Guinness
    -0.61
     slang
    -0.60
     "-
    -0.60
    POSITIVE LOGITS
     underscores
    0.92
     illuminating
    0.92
     empir
    0.90
     underscore
    0.87
     empirical
    0.87
     miscon
    0.86
     illuminate
    0.83
    orthy
    0.83
     undersc
    0.82
     troubling
    0.82
    Activations Density 0.620%

    No Known Activations