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. 7-RES-JB
    6. 13095
    Prev
    Next
    INDEX
    Explanations

    commands or prompts starting with "Let's."

    oai_token-act-pair · gpt-3.5-turbo

    phrases or symbols that indicate commands or actions, particularly in the context of software interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.84
     seiz
    -0.71
     Annotations
    -0.70
     lodging
    -0.68
     Seym
    -0.68
     mosqu
    -0.66
     tremend
    -0.65
    çīĪ
    -0.65
     horizont
    -0.64
     transmitter
    -0.64
    POSITIVE LOGITS
    ķ
    0.89
    ı
    0.89
    ĵ
    0.86
    º
    0.84
    Ľ
    0.84
    £
    0.83
    ulty
    0.81
    ongo
    0.80
    Ĵ
    0.80
    ĭ
    0.78
    Activations Density 0.080%

    No Known Activations