© 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. 13293
    Prev
    Next
    INDEX
    Explanations

    words related to emphasizing or pointing out significant information or details

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "fact."

    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
     livest
    -0.66
    ascus
    -0.60
    dain
    -0.57
    Refer
    -0.55
     accomp
    -0.54
    )}
    -0.54
     administ
    -0.53
    /**
    -0.52
    jong
    -0.52
     streng
    -0.52
    POSITIVE LOGITS
     that
    1.20
    uality
    1.03
    orial
    1.00
     THAT
    0.99
    ional
    0.94
    that
    0.94
    ually
    0.88
    oid
    0.82
    oids
    0.80
    finder
    0.72
    Activations Density 0.045%

    No Known Activations