© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 289
    Prev
    Next
    INDEX
    Explanations

    references to the term "nerd" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "nerd" and related terms

    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
     Cipher
    -0.64
     Telegram
    -0.62
     simulator
    -0.62
     caution
    -0.61
     Improvement
    -0.61
     unmarked
    -0.60
     LIA
    -0.60
     labour
    -0.56
     viol
    -0.55
     Clerk
    -0.55
    POSITIVE LOGITS
    getic
    1.13
    dy
    1.12
    ds
    1.11
    ding
    1.10
    fed
    0.99
    vana
    0.95
    gie
    0.94
    der
    0.91
    oji
    0.90
    dt
    0.89
    Activations Density 0.082%

    No Known Activations