© 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. 13341
    Prev
    Next
    INDEX
    Explanations

    proper nouns with specific reference to different entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific games and gaming terminology

    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
     famously
    -0.48
     notoriously
    -0.44
     cheers
    -0.43
     rhy
    -0.43
     exacerbated
    -0.42
     sped
    -0.41
     joking
    -0.41
     headlines
    -0.41
     convincing
    -0.40
     pronounced
    -0.40
    POSITIVE LOGITS
    ratom
    0.57
    Sphere
    0.55
    Wiki
    0.55
    oplan
    0.54
    Đ
    0.54
    Ă
    0.54
    Ě
    0.54
    0.54
    ğ
    0.54
    ÿ
    0.54
    Activations Density 1.475%

    No Known Activations