© 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 EvalsExportsinterp-engineNEWAPI 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. 20740
    Prev
    Next
    INDEX
    Explanations

    fruit-related nouns and adjectives

    oai_token-act-pair · gpt-3.5-turbo

    references to music, flavors, and preferences

    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
    âĢł
    -0.74
    ãĥ©ãĥ³
    -0.71
    ãĤ¿
    -0.66
    accompan
    -0.66
    âĹ¼
    -0.65
    å£
    -0.64
    éŃĶ
    -0.63
    æł
    -0.62
    áµ
    -0.60
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.60
    POSITIVE LOGITS
     anymore
    1.45
     either
    1.42
     nor
    1.15
     whatsoever
    1.15
     slightest
    1.14
    yet
    1.12
    nor
    1.12
     anyway
    1.01
     :(
    1.00
     necessarily
    0.97
    Activations Density 0.478%

    No Known Activations