© 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. 20869
    Prev
    Next
    INDEX
    Explanations

    words related to information dissemination or communication, such as "notifying," "informed," "advising," and "warned."

    oai_token-act-pair · gpt-3.5-turbo

    words related to communication and notification

    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
    adesh
    -0.96
    Untitled
    -0.73
    arthy
    -0.73
    avascript
    -0.72
    artney
    -0.71
    artifacts
    -0.71
    Interstitial
    -0.70
    é¾įåĸļ士
    -0.68
    redits
    -0.66
    ottesville
    -0.66
    POSITIVE LOGITS
     us
    1.12
     him
    1.10
     them
    1.05
     me
    1.00
     superiors
    0.98
     everyone
    0.86
     customers
    0.84
     residents
    0.84
     employees
    0.84
     landowners
    0.83
    Activations Density 0.130%

    No Known Activations