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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23808
    Prev
    Next
    INDEX
    Explanations

    keywords related to symposiums or symphonies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of symposiums and conferences

    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
     sow
    -0.64
     proportional
    -0.63
     mileage
    -0.59
     Palmer
    -0.59
    ating
    -0.58
     domestically
    -0.58
     Shoot
    -0.58
     Garry
    -0.58
    hips
    -0.57
    ate
    -0.57
    POSITIVE LOGITS
    posium
    1.75
    phony
    1.37
    ptoms
    1.29
    enter
    1.13
    pt
    1.10
    antics
    1.06
    chron
    1.04
    ony
    1.03
    ptic
    1.01
    onds
    0.98
    Activations Density 0.051%

    No Known Activations