© 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. 5796
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "Hey" or "Oh."

    oai_token-act-pair · gpt-3.5-turbo

    informal conversational phrases and expressions

    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
    etheless
    -0.89
    Contents
    -0.76
    ioned
    -0.76
    quickShipAvailable
    -0.73
    upon
    -0.72
    channelAvailability
    -0.70
     "<
    -0.68
     "...
    -0.67
    CENT
    -0.67
    jri
    -0.67
    POSITIVE LOGITS
    ,'"
    1.71
    ',"
    1.70
    '."
    1.66
    !'"
    1.65
    ?'"
    1.59
    .'"
    1.58
    '"
    1.38
    ').
    1.10
    ']
    1.09
    ?'
    1.09
    Activations Density 0.281%

    No Known Activations