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. 9878
    Prev
    Next
    INDEX
    Explanations

    instances of the number 24

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the number 24 in context of time or duration

    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
    enegger
    -0.98
    atown
    -0.90
     Beir
    -0.89
    ovie
    -0.82
    issors
    -0.80
    atchewan
    -0.80
    feature
    -0.79
    ippi
    -0.77
    EStream
    -0.74
    ype
    -0.73
    POSITIVE LOGITS
    teen
    0.89
     livest
    0.83
    ©¶æ¥µ
    0.81
    th
    0.78
    24
    0.77
    hours
    0.76
    72
    0.76
    00
    0.75
    576
    0.74
    96
    0.74
    Activations Density 0.022%

    No Known Activations