© 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. 20960
    Prev
    Next
    INDEX
    Explanations

    scientific and research-related terms

    oai_token-act-pair · gpt-3.5-turbo

    scientific discoveries and their implications

    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
     Theft
    -0.82
     Owners
    -0.74
     grievances
    -0.73
     Franch
    -0.72
     Ratings
    -0.71
    Exit
    -0.69
    alsh
    -0.69
     lockout
    -0.66
     hating
    -0.66
     Oath
    -0.66
    POSITIVE LOGITS
     discoveries
    1.24
     scientists
    1.24
     tantal
    1.23
     breakthrough
    1.22
     exciting
    1.20
    Scientists
    1.19
     Scientists
    1.18
    Explore
    1.17
     physicists
    1.17
     biologists
    1.16
    Activations Density 0.438%

    No Known Activations