© 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. 11-RES-JB
    11. 14862
    Prev
    Next
    INDEX
    Explanations

    words related to personal experiences and physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal growth and perseverance

    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
     Armageddon
    -0.77
     Kissinger
    -0.75
     Powell
    -0.72
     recounted
    -0.70
     reprinted
    -0.70
     Keynes
    -0.70
     Windsor
    -0.70
     eyewitness
    -0.69
     curs
    -0.69
     Hutchinson
    -0.68
    POSITIVE LOGITS
    âĢ
    1.23
    âĶ
    1.16
    [/
    1.09
    âĹ
    1.01
    ï¸ı
    1.01
    ã
    0.97
     wanna
    0.96
    âĸ
    0.95
    ngth
    0.93
    ///
    0.93
    Activations Density 0.604%

    No Known Activations