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. 19812
    Prev
    Next
    INDEX
    Explanations

    email-related prompts requesting users to re-enter an email address

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enter" in various contexts

    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
    illard
    -0.69
     jud
    -0.67
    Ĭ±
    -0.67
     polic
    -0.65
     hefty
    -0.62
     merciless
    -0.62
     lofty
    -0.62
     tremend
    -0.61
     superhuman
    -0.61
     nuns
    -0.59
    POSITIVE LOGITS
    prise
    1.56
    prises
    1.46
    enter
    1.19
    tainment
    0.97
    TAIN
    0.90
    taining
    0.86
    prising
    0.82
    ology
    0.81
    itus
    0.80
    ATURES
    0.78
    Activations Density 0.006%

    No Known Activations