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. 1540
    Prev
    Next
    INDEX
    Explanations

    words related to speed or quickness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fast."

    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
    cules
    -0.82
    xual
    -0.74
    ongyang
    -0.72
    pheus
    -0.72
     Helpful
    -0.70
    vironment
    -0.69
    ignty
    -0.68
    ĨĴ
    -0.68
    æ©
    -0.68
     Theatre
    -0.67
    POSITIVE LOGITS
    idious
    1.21
     paced
    1.18
    fast
    0.97
    ened
    0.97
    cgi
    0.95
     fast
    0.91
    boot
    0.90
    eners
    0.82
    nesses
    0.81
     asleep
    0.76
    Activations Density 0.011%

    No Known Activations