© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10183
    Prev
    Next
    INDEX
    Explanations

    beauty pageant winners and memorable years

    oai_token-act-pair · gpt-3.5-turbo

    information related to numerical data and dates

    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
     tremend
    -0.76
    é¾įåĸļ士
    -0.70
     glim
    -0.69
    zos
    -0.68
     corrid
    -0.68
    Root
    -0.68
    Score
    -0.68
    oke
    -0.67
    Ze
    -0.66
    othe
    -0.65
    POSITIVE LOGITS
     1995
    1.73
     1996
    1.72
     1990
    1.71
     1993
    1.71
     1992
    1.71
     1997
    1.71
     1994
    1.71
     1991
    1.68
     1999
    1.68
     1998
    1.65
    Activations Density 0.050%

    No Known Activations