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. 19105
    Prev
    Next
    INDEX
    Explanations

    time intervals, specifically mentioning 'and a half'

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate time duration or intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    CLA
    -0.61
    BG
    -0.61
    dayName
    -0.60
    gen
    -0.58
    FU
    -0.58
    ippi
    -0.58
    Enhanced
    -0.58
    heny
    -0.57
    PRES
    -0.57
    udence
    -0.57
    POSITIVE LOGITS
    rogen
    0.82
    rogens
    0.78
    romeda
    0.75
     therefore
    0.73
     counting
    0.72
    rew
    0.69
     quart
    0.69
     consequently
    0.69
     ½
    0.67
     half
    0.64
    Activations Density 0.091%

    No Known Activations