© 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. 11-RES-JB
    11. 7770
    Prev
    Next
    INDEX
    Explanations

    technical terms related to music and art

    oai_token-act-pair · gpt-3.5-turbo

    elements related to artistic accomplishments and contributions

    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
     bye
    -0.74
     THEIR
    -0.63
    glers
    -0.62
     moms
    -0.62
     disadvantage
    -0.60
    cmp
    -0.59
     Becky
    -0.58
     Lumpur
    -0.58
     spokeswoman
    -0.56
    ouple
    -0.56
    POSITIVE LOGITS
    his
    1.21
    His
    1.13
     his
    1.05
     himself
    1.00
     autobiography
    0.99
     His
    0.95
     autobi
    0.95
    He
    0.93
     he
    0.88
     eloqu
    0.83
    Activations Density 0.740%

    No Known Activations