Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23505
    Prev
    Next
    INDEX
    Explanations

    temperatures or numerical values related to specific degrees

    oai_token-act-pair · gpt-3.5-turbo

    numerical values related to temperature and cooking instructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.69
    alien
    -0.66
     Creator
    -0.65
     forgotten
    -0.63
     Telegram
    -0.61
    ophon
    -0.60
    atto
    -0.60
     Spending
    -0.59
    book
    -0.59
     disband
    -0.59
    POSITIVE LOGITS
    mph
    1.48
     degrees
    1.48
    °
    1.39
     mph
    1.33
    deg
    1.29
    º
    1.29
    Hz
    1.26
     MPH
    1.25
     °
    1.20
     Hz
    1.19
    Activations Density 0.084%

    No Known Activations