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. 9662
    Prev
    Next
    INDEX
    Explanations

    phrases related to contentious or controversial topics or opinions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social issues and cultural perceptions

    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
    eatures
    -0.65
    swick
    -0.59
     VIDEOS
    -0.59
    ggles
    -0.58
     redes
    -0.56
     confir
    -0.55
    arthed
    -0.54
    acia
    -0.53
    everal
    -0.53
    OTOS
    -0.53
    POSITIVE LOGITS
     because
    1.09
     somehow
    1.08
     unfairly
    1.03
     rather
    0.96
    ?,
    0.95
     anymore
    0.94
     whereas
    0.90
     or
    0.89
     despite
    0.87
     deserving
    0.86
    Activations Density 0.490%

    No Known Activations