© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 10190
    Prev
    Next
    INDEX
    Explanations

    comparisons in terms of quantity or degree

    oai_token-act-pair · gpt-3.5-turbo

    comparative terms or phrases indicating degree

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.88
    iversary
    -0.81
    ãĤ¡
    -0.81
     Brus
    -0.78
     Anniversary
    -0.71
    andel
    -0.69
    imation
    -0.69
     spills
    -0.67
    =-=-
    -0.67
    ãĥ¼ãĥĨãĤ£
    -0.67
    POSITIVE LOGITS
     interested
    1.37
     aware
    1.32
     obsessed
    1.29
     willing
    1.23
     knowledgeable
    1.20
     proficient
    1.20
     skilled
    1.20
     afraid
    1.20
     concerned
    1.18
     confident
    1.17
    Activations Density 0.265%

    No Known Activations