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. 8-RES-JB
    6. 14764
    Prev
    Next
    INDEX
    Explanations

    photographs with captions indicating a specific date, location, and photographer

    oai_token-act-pair · gpt-3.5-turbo

    instances of photo credits or attributions in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osc
    -0.81
    rencies
    -0.72
    oscope
    -0.69
    powers
    -0.66
    eeper
    -0.66
    flo
    -0.64
    ocrates
    -0.64
    uilding
    -0.62
    omnia
    -0.61
    oshenko
    -0.61
    POSITIVE LOGITS
     Courtesy
    0.94
    /)
    0.85
     Photo
    0.84
     courtesy
    0.81
    )"
    0.74
     Everett
    0.74
    )(
    0.72
     COURT
    0.71
    Photo
    0.71
     Credit
    0.71
    Activations Density 0.031%

    No Known Activations