© 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. 2740
    Prev
    Next
    INDEX
    Explanations

    places or settings where certain actions or events are likely to take place

    oai_token-act-pair · gpt-3.5-turbo

    references to religious or educational institutions and gatherings

    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
    immers
    -0.85
    brids
    -0.84
    umbs
    -0.81
    Images
    -0.81
    awatts
    -0.80
    bugs
    -0.80
     Views
    -0.80
    bits
    -0.80
     Medals
    -0.79
     Shards
    -0.79
    POSITIVE LOGITS
     venue
    1.14
     gym
    1.12
     environment
    1.09
     institution
    1.09
     event
    1.08
     theatre
    1.08
     workshop
    1.07
     monastery
    1.07
     theater
    1.07
     clinic
    1.07
    Activations Density 0.405%

    No Known Activations