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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 8119
    Prev
    Next
    INDEX
    Explanations

    phrases related to secret operations or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to social commentary or critique

    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
    ebin
    -0.91
    Rated
    -0.88
    Recommend
    -0.87
    enthal
    -0.87
    Solution
    -0.85
    Secondly
    -0.81
    `.
    -0.81
    Materials
    -0.80
    Dialogue
    -0.79
    ****************
    -0.78
    POSITIVE LOGITS
     flashy
    1.40
     glamorous
    1.20
     sleek
    1.17
     glam
    1.14
     cheesy
    1.12
     goofy
    1.11
     slick
    1.10
     fancy
    1.10
     gimm
    1.09
     glossy
    1.09
    Activations Density 0.840%

    No Known Activations