© 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. 5697
    Prev
    Next
    INDEX
    Explanations

    words related to statistics, measurement, margins, and deviations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate comparison or alternatives

    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
    STER
    -0.72
    oke
    -0.68
    anners
    -0.66
     Newspaper
    -0.66
     Drink
    -0.64
     Grill
    -0.63
     Bullets
    -0.62
    nikov
    -0.60
     Shelter
    -0.60
    wolf
    -0.60
    POSITIVE LOGITS
     minus
    1.18
    minus
    0.97
     equals
    0.97
     exceed
    0.92
     complement
    0.92
    equal
    0.92
     exceeds
    0.91
     antip
    0.90
     surpass
    0.90
     contrasting
    0.89
    Activations Density 0.081%

    No Known Activations