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. 21544
    Prev
    Next
    INDEX
    Explanations

    sentences or statements that convey locations or actions related to gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to scenes or actions happening in various locations

    oai_token-act-pair · gpt-3.5-turbo
    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
    thal
    -0.92
    é»Ĵ
    -0.76
    Thumbnail
    -0.76
     utilize
    -0.75
    GF
    -0.72
     independ
    -0.71
     commer
    -0.70
     dimensional
    -0.69
    BRE
    -0.69
    tesy
    -0.68
    POSITIVE LOGITS
     But
    1.16
     Occasionally
    1.12
     Worse
    1.09
     Others
    1.07
     And
    1.06
     Everywhere
    1.06
     Yet
    1.04
     Suddenly
    1.03
     Amid
    1.02
     Sometimes
    1.01
    Activations Density 0.733%

    No Known Activations