© 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. 3477
    Prev
    Next
    INDEX
    Explanations

    references to SD cards and storage capabilities

    oai_token-act-pair · gpt-3.5-turbo

    references to memory storage components, particularly SD cards

    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
    worms
    -0.72
    enberg
    -0.72
    enburg
    -0.69
    advertising
    -0.68
    cock
    -0.66
    press
    -0.65
    terday
    -0.64
    ussen
    -0.63
    ches
    -0.63
    ises
    -0.63
    POSITIVE LOGITS
    ocument
    1.05
    HC
    0.98
    IFF
    0.93
    LP
    0.93
     card
    0.92
     CARD
    0.91
    CC
    0.90
     Slot
    0.86
     Cards
    0.82
     cards
    0.81
    Activations Density 0.038%

    No Known Activations