© 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. 11-RES-JB
    11. 14621
    Prev
    Next
    INDEX
    Explanations

    words related to actions and processes, such as "blocking," "causing," "seeing," "cleaning," "helping," and "supporting."

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" frequently used in various contexts

    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
    ledged
    -0.73
    rued
    -0.72
    scribe
    -0.70
    arton
    -0.68
    lated
    -0.67
    prus
    -0.67
    cised
    -0.65
    aceae
    -0.65
    ?????-
    -0.62
    =-=-
    -0.62
    POSITIVE LOGITS
     letting
    1.59
     delivering
    1.59
     distributing
    1.59
     putting
    1.58
     making
    1.57
     maintaining
    1.55
     providing
    1.54
     submitting
    1.54
     sending
    1.53
     discovering
    1.53
    Activations Density 0.316%

    No Known Activations