© 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 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. 9-RES-JB
    11. 4604
    Prev
    Next
    INDEX
    Explanations

    sentences containing phrases emphasizing a specific degree or aspect

    oai_token-act-pair · gpt-3.5-turbo

    the indefinite article "a" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Izan
    -0.70
     Anaheim
    -0.69
    skirts
    -0.64
    letters
    -0.63
     memos
    -0.63
     Elections
    -0.61
     Ort
    -0.60
     instructions
    -0.60
    outs
    -0.60
    Exception
    -0.59
    POSITIVE LOGITS
     cohesive
    1.15
     coherent
    1.12
     meaningful
    1.12
     reasonable
    1.11
    rouse
    1.07
     lot
    1.06
     decent
    1.04
     realistic
    1.01
     positive
    1.00
     tangible
    0.98
    Activations Density 0.395%

    No Known Activations