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. 3-RES-JB
    6. 7702
    Prev
    Next
    INDEX
    Explanations

    titles or mentions of individuals with the last name "Morris" or "Ris"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ris."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.87
     EntityItem
    -0.74
    erm
    -0.71
    eatures
    -0.70
    ¥ŀ
    -0.69
    resso
    -0.68
    ļé
    -0.64
    nesium
    -0.64
     Calories
    -0.61
    club
    -0.61
    POSITIVE LOGITS
    sey
    0.98
    ques
    0.89
    quez
    0.87
    pect
    0.83
    zon
    0.83
    py
    0.79
    pent
    0.79
    andra
    0.77
    pan
    0.77
    anchez
    0.76
    Activations Density 0.008%

    No Known Activations