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. 20175
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a state or occurrence happening or being true

    oai_token-act-pair · gpt-3.5-turbo

    statements that indicate applicability or validity of claims or theories

    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
    ICO
    -0.62
    tten
    -0.62
    heit
    -0.62
    });
    -0.59
    >[
    -0.57
    )))
    -0.56
     Monstrous
    -0.56
     Released
    -0.56
     Encyclopedia
    -0.56
    urus
    -0.56
    POSITIVE LOGITS
     everywhere
    1.11
     chiefly
    1.11
     especially
    1.09
     mainly
    1.07
     wherever
    1.06
     primarily
    1.05
     irrespective
    1.04
    especially
    1.02
     principally
    1.01
     regardless
    1.00
    Activations Density 0.451%

    No Known Activations