© 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. 4124
    Prev
    Next
    INDEX
    Explanations

    medical terms related to undiagnosed or medical conditions that are difficult to identify

    oai_token-act-pair · gpt-3.5-turbo

    words and roots associated with concepts of undermining, inefficacy, or deficiency

    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
     Cosponsors
    -0.74
     misses
    -0.72
    loo
    -0.71
    hs
    -0.65
     coughing
    -0.65
    ships
    -0.63
     smokes
    -0.62
     miss
    -0.62
     QC
    -0.60
     helpers
    -0.60
    POSITIVE LOGITS
    initely
    1.10
    ministic
    1.10
    rimination
    1.05
    inguished
    1.01
    inished
    1.00
    ect
    0.98
    puted
    0.97
    ected
    0.97
    inguishable
    0.96
    usional
    0.95
    Activations Density 0.060%

    No Known Activations