© 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. 13289
    Prev
    Next
    INDEX
    Explanations

    instances where a project is being discussed or described

    oai_token-act-pair · gpt-3.5-turbo

    statements about future plans or projects

    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
    76561
    -0.77
     hating
    -0.72
     Deaths
    -0.70
     dies
    -0.69
    hea
    -0.68
     dying
    -0.68
     misses
    -0.67
     faked
    -0.62
     Metatron
    -0.61
     Died
    -0.60
    POSITIVE LOGITS
     consist
    1.33
     comprise
    1.28
     include
    1.22
     encompass
    1.19
     entail
    1.14
     involve
    1.13
     incorporate
    1.12
     enable
    1.10
     integrate
    1.09
     allow
    1.06
    Activations Density 0.166%

    No Known Activations