© 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. 14247
    Prev
    Next
    INDEX
    Explanations

    phrases where individuals express a desire or intention to become involved in a particular group or community

    oai_token-act-pair · gpt-3.5-turbo

    phrases about belonging and participation

    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
     ceilings
    -0.65
    stasy
    -0.61
     heights
    -0.54
    geries
    -0.52
     levels
    -0.50
     backgrounds
    -0.50
     appre
    -0.48
     widest
    -0.48
    opa
    -0.48
     resh
    -0.47
    POSITIVE LOGITS
    aking
    1.08
    akers
    1.00
    ridge
    0.95
     of
    0.92
    aken
    0.90
    aker
    0.90
     thereof
    0.87
    iers
    0.82
    ook
    0.81
     OF
    0.77
    Activations Density 0.047%

    No Known Activations