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. 1-RES-JB
    6. 23878
    Prev
    Next
    INDEX
    Explanations

    the name "Gemma" in various phrases and contexts

    oai_token-act-pair · gpt-3.5-turbo

    the name "Gemma" and its variations, indicating a focus on a character or person with that name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.89
    etheless
    -0.78
    icular
    -0.75
    erness
    -0.74
    distance
    -0.68
     congressman
    -0.66
     lumber
    -0.64
     elected
    -0.64
    ional
    -0.64
     skirts
    -0.64
    POSITIVE LOGITS
    gem
    1.27
     Gem
    1.19
    atsu
    0.85
    esa
    0.80
    abyte
    0.79
    nai
    0.78
    gob
    0.78
    OSH
    0.77
    ellar
    0.77
    RI
    0.76
    Activations Density 0.021%

    No Known Activations