© 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. 2525
    Prev
    Next
    INDEX
    Explanations

    lead authors and researchers of studies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of authors and their roles in research studies

    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
    interrupted
    -0.65
     hairc
    -0.61
    conservancy
    -0.58
     destro
    -0.56
     necessities
    -0.55
     blat
    -0.54
     fung
    -0.54
    BUS
    -0.54
    atron
    -0.54
     negatives
    -0.53
    POSITIVE LOGITS
    hesis
    0.82
     of
    0.77
     Investigator
    0.77
     Professor
    0.76
    atories
    0.73
     author
    0.73
     authors
    0.72
    essors
    0.72
    writer
    0.71
    heses
    0.70
    Activations Density 0.105%

    No Known Activations