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. 19939
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Madras

    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
     Yankee
    -0.70
    tails
    -0.69
    glers
    -0.68
    ĵ
    -0.66
    tains
    -0.62
     lockout
    -0.61
    ĨĴ
    -0.59
     Clarkson
    -0.59
     warrants
    -0.58
     favors
    -0.58
    POSITIVE LOGITS
    irez
    1.06
    quez
    1.00
    hea
    0.99
    arin
    0.99
    ques
    0.98
    xual
    0.97
    yout
    0.96
    ourced
    0.94
    sembly
    0.94
    ources
    0.93
    Activations Density 0.017%

    No Known Activations