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. 8477
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to a location or concept associated with "Sumatra."

    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
    RAFT
    -0.73
    ussen
    -0.71
    Downloadha
    -0.69
    avorite
    -0.68
     tradem
    -0.64
     supervised
    -0.64
     retail
    -0.62
    tumblr
    -0.62
     broadband
    -0.61
    minecraft
    -0.61
    POSITIVE LOGITS
     Sum
    1.18
    ming
    1.14
    sum
    1.09
    Sum
    1.07
    mits
    1.03
    mons
    0.97
    mers
    0.93
    itar
    0.90
    otaur
    0.88
    mite
    0.79
    Activations Density 0.006%

    No Known Activations