© 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. 6031
    Prev
    Next
    INDEX
    Explanations

    statements or comments made by individuals

    oai_token-act-pair · gpt-3.5-turbo

    statements related to social commentary and political opinions

    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
    !'
    -0.76
    ®,
    -0.75
    *.
    -0.68
     sqor
    -0.67
     extraord
    -0.64
     hilar
    -0.62
     badass
    -0.61
    schild
    -0.61
     marvelous
    -0.61
    */
    -0.61
    POSITIVE LOGITS
     ''
    0.90
     "
    0.89
     "...
    0.78
     "'
    0.77
     "[
    0.76
     counselling
    0.75
     "(
    0.72
    20439
    0.72
     councillors
    0.66
     apologised
    0.66
    Activations Density 1.380%

    No Known Activations