© 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 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. 15855
    Prev
    Next
    INDEX
    Explanations

    statements related to proving oneself or demonstrating something to others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of proving oneself or demonstrating capabilities

    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
     captcha
    -0.78
     Variant
    -0.71
     pse
    -0.70
    etting
    -0.70
     revolving
    -0.66
    ascript
    -0.65
    lihood
    -0.65
    ieri
    -0.64
     sugg
    -0.64
    acci
    -0.62
    POSITIVE LOGITS
     appreciation
    1.03
     superiority
    0.92
     dominance
    0.88
     solidarity
    0.85
     displeasure
    0.85
     gratitude
    0.83
     kindness
    0.80
     individuality
    0.76
    biz
    0.75
     defiance
    0.74
    Activations Density 0.186%

    No Known Activations