© 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. 12348
    Prev
    Next
    INDEX
    Explanations

    phrases related to heights or spatial positions

    oai_token-act-pair · gpt-3.5-turbo

    references to popular culture or specific titles of works

    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
     rele
    -0.80
     manageable
    -0.80
     emulation
    -0.79
     involuntary
    -0.79
     recall
    -0.78
     worthwhile
    -0.78
     appre
    -0.77
     toler
    -0.76
     referen
    -0.76
     pity
    -0.76
    POSITIVE LOGITS
     Tracks
    1.36
     Skies
    1.33
     Trees
    1.28
     Bottle
    1.27
     Curve
    1.24
     Beginning
    1.24
     Past
    1.23
     Seas
    1.22
     Clouds
    1.22
     Lines
    1.21
    Activations Density 0.087%

    No Known Activations