© 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. 929
    Prev
    Next
    INDEX
    Explanations

    mentions of specific months and numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to specific dates, months, and numerical details within the text

    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
     Berk
    -0.93
     Chung
    -0.88
     Gree
    -0.87
     PLA
    -0.83
     Bok
    -0.83
    ela
    -0.82
     Braun
    -0.82
     Kel
    -0.81
     Bra
    -0.80
    Bra
    -0.80
    POSITIVE LOGITS
    11
    1.23
     11
    1.18
    117
    1.08
     117
    1.06
     115
    1.04
    111
    1.03
    114
    1.01
     111
    1.00
    112
    0.99
    116
    0.98
    Activations Density 0.484%

    No Known Activations