© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18432
    Prev
    Next
    INDEX
    Explanations

    words related to attitudes or behavior

    oai_token-act-pair · gpt-3.5-turbo

    references to attitudes or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.89
    icles
    -0.86
    dry
    -0.76
    oval
    -0.72
    icle
    -0.69
    idden
    -0.67
    aban
    -0.67
    Interstitial
    -0.66
    rake
    -0.66
    icular
    -0.66
    POSITIVE LOGITS
     toward
    1.50
     towards
    1.41
     attitude
    1.15
     Towards
    1.12
     attitudes
    0.95
     Tow
    0.94
     stance
    0.79
    uation
    0.75
     demeanor
    0.73
     hostility
    0.72
    Activations Density 0.039%

    No Known Activations