© 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. 11586
    Prev
    Next
    INDEX
    Explanations

    keywords related to initiating activities or processes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to launching initiatives or investigations

    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
    èĢħ
    -0.72
    ables
    -0.70
     discharged
    -0.65
     coefficients
    -0.64
     attendees
    -0.62
    ABLE
    -0.62
     Rasm
    -0.61
    Reason
    -0.61
     definitions
    -0.60
    ĭ
    -0.59
    POSITIVE LOGITS
     crusade
    1.38
     concerted
    1.11
     campaign
    1.11
     Crusade
    1.08
     crackdown
    1.08
     smear
    1.04
     blitz
    1.00
     relentless
    0.99
     purge
    0.97
     futile
    0.96
    Activations Density 0.240%

    No Known Activations