© 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. 0-RES-JB
    11. 5345
    Prev
    Next
    INDEX
    Explanations

    words related to the profession of a "writer"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "iterator."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blu
    -0.73
     flares
    -0.63
     cooling
    -0.60
     such
    -0.58
     mail
    -0.57
     sadd
    -0.56
     Apollo
    -0.56
     Flare
    -0.56
     Avalon
    -0.55
     Mechdragon
    -0.55
    POSITIVE LOGITS
    iter
    4.90
    iterator
    1.52
    iting
    1.50
    Iter
    1.36
     iter
    1.26
    itter
    1.20
    ite
    1.19
    itation
    1.19
    ites
    1.14
    ited
    1.13
    Activations Density 0.017%

    No Known Activations