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. 9-RES-JB
    6. 3839
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings and substances like licenses, warrants, chicken, beef, and buckle, or thematic elements like climate crisis, solar eclipse, and community

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¾įåĸļ士
    -0.76
    ãĤ¤ãĥĪ
    -0.75
    æ©
    -0.74
    é¾įå
    -0.71
    »Ĵ
    -0.69
    éŃĶ
    -0.66
    ãĥĥ
    -0.66
    gro
    -0.64
    ãĤ¨ãĥ«
    -0.64
    YN
    -0.62
    POSITIVE LOGITS
     simulator
    0.67
     doesnt
    0.63
     fiasco
    0.63
     sucks
    0.61
     hangs
    0.60
     crap
    0.59
     meets
    0.58
    ®
    0.57
     âĢº
    0.57
     debacle
    0.57
    Activations Density 0.651%

    No Known Activations