© 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. 13449
    Prev
    Next
    INDEX
    Explanations

    terms related to opposition or resistance against a particular idea or group

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of opposition or hostility towards specific groups or ideas

    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
     Sins
    -0.65
     Suc
    -0.60
     concerned
    -0.58
    hower
    -0.56
     Nights
    -0.55
    cific
    -0.54
     ages
    -0.53
    ecause
    -0.53
     Sketch
    -0.53
     Halls
    -0.52
    POSITIVE LOGITS
    war
    1.23
    abortion
    1.23
    establishment
    1.22
    hero
    1.09
    -
    1.06
    -[
    1.03
    Semitic
    1.00
    Fa
    0.99
    -"
    0.96
    immigrant
    0.95
    Activations Density 0.030%

    No Known Activations