Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4325
    Prev
    Next
    INDEX
    Explanations

    names of sports players

    oai_token-act-pair · gpt-3.5-turbo

    various forms of parentheses

    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
     contempor
    -0.81
     tabloid
    -0.77
     genre
    -0.76
     nature
    -0.75
     propag
    -0.74
     breed
    -0.74
     ram
    -0.73
     variations
    -0.73
     perme
    -0.72
     refreshing
    -0.72
    POSITIVE LOGITS
    seven
    1.53
    nine
    1.52
    fifth
    1.51
    six
    1.51
    fourth
    1.49
    eight
    1.49
    four
    1.48
    three
    1.46
    third
    1.46
    five
    1.44
    Activations Density 0.111%

    No Known Activations