© 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. 12-RES-JB
    11. 4417
    Prev
    Next
    INDEX
    Explanations

    dates mentioned in the document

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    time-related expressions and scheduling details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ©¶æ¥µ
    -0.84
     teasp
    -0.83
    ãĥ¯ãĥ³
    -0.81
    Ĕ
    -0.80
    ă
    -0.80
    -0.80
    ò
    -0.80
    Ą
    -0.80
    Á
    -0.79
    Ā
    -0.79
    POSITIVE LOGITS
     noon
    1.10
     Oct
    1.09
     Sept
    1.09
     Aug
    1.08
     Feb
    1.07
     midnight
    1.07
     Nov
    1.04
     Dec
    1.04
     midday
    1.03
     Jan
    1.02
    Activations Density 0.238%

    No Known Activations