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. 10-RES-JB
    6. 3719
    Prev
    Next
    INDEX
    Explanations

    salacious and explicit content involving a woman's character

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical data or references to statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     foc
    -0.92
     favour
    -0.79
     stabil
    -0.78
     sided
    -0.76
     exha
    -0.75
     encomp
    -0.75
     util
    -0.75
     tram
    -0.75
     enqu
    -0.73
     incub
    -0.73
    POSITIVE LOGITS
    WASHINGTON
    1.76
    SAN
    1.60
    LOS
    1.53
    Amid
    1.48
    When
    1.48
    NEW
    1.47
    Sometimes
    1.46
    Imagine
    1.41
    DEN
    1.41
    By
    1.40
    Activations Density 0.212%

    No Known Activations