© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 2329
    Prev
    Next
    INDEX
    Explanations

    phrases related to extremist views or ideologies

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    elements related to societal problems and their underlying ideological influences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    endars
    -0.89
    options
    -0.80
    ittees
    -0.79
    udget
    -0.79
    ea
    -0.78
    wk
    -0.78
     Investments
    -0.77
    amera
    -0.73
    ovies
    -0.73
     Updates
    -0.72
    POSITIVE LOGITS
     flaw
    1.29
     trait
    1.26
     characteristic
    1.25
     pathology
    1.22
     paradox
    1.18
     weakness
    1.17
     symptom
    1.16
     pecul
    1.14
     obstacle
    1.12
     drawback
    1.12
    Activations Density 0.305%

    No Known Activations