© 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. 7696
    Prev
    Next
    INDEX
    Explanations

    phrases related to new possibilities or experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to previously unthought-of possibilities or opportunities

    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
    asma
    -0.63
    ammy
    -0.60
     arrang
    -0.59
     confir
    -0.58
     Miche
    -0.57
     Ammo
    -0.57
    sted
    -0.56
     Matthews
    -0.55
    interstitial
    -0.55
     Adjusted
    -0.54
    POSITIVE LOGITS
     otherwise
    1.54
     previously
    1.30
     hitherto
    1.28
     ordinarily
    1.11
     unimaginable
    1.11
     never
    1.10
     normally
    1.08
     hadn
    1.07
     unthinkable
    1.03
     traditionally
    1.00
    Activations Density 0.378%

    No Known Activations