© 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. 21003
    Prev
    Next
    INDEX
    Explanations

    words related to potential causes or factors contributing to various societal issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a relationship between social issues and contributing factors

    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
    phabet
    -0.80
    ISO
    -0.75
    reet
    -0.73
    estyles
    -0.72
    UTF
    -0.69
     wraps
    -0.69
    Dialogue
    -0.68
    aram
    -0.67
    orned
    -0.66
     Sear
    -0.65
    POSITIVE LOGITS
     culprit
    1.56
     causes
    1.49
     causation
    1.48
     cause
    1.45
     motive
    1.41
     factors
    1.40
     contribut
    1.39
     blame
    1.39
     factor
    1.37
     contributing
    1.33
    Activations Density 0.407%

    No Known Activations