© 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. 14027
    Prev
    Next
    INDEX
    Explanations

    words related to uncovering, discovering, and revealing hidden or underlying aspects of information

    oai_token-act-pair · gpt-3.5-turbo

    action words and processes related to discovery, evaluation, and conflict

    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
    •shakespeare
    hidden!

    No Comments

    Negative Logits
     sidx
    -0.65
     reper
    -0.65
    ULTS
    -0.64
     Haram
    -0.54
    pei
    -0.53
    Downloadha
    -0.53
     Orchestra
    -0.52
     Nare
    -0.52
    OPLE
    -0.51
     tatt
    -0.49
    POSITIVE LOGITS
    ing
    3.36
    ed
    1.95
    ING
    1.82
    ingly
    1.62
    ings
    1.54
    edIn
    1.50
    edly
    1.41
    ging
    1.40
    ingham
    1.39
    ership
    1.38
    Activations Density 0.728%

    No Known Activations