© 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. 10-RES-JB
    11. 5859
    Prev
    Next
    INDEX
    Explanations

    words related to perseverance and dedication

    oai_token-act-pair · gpt-3.5-turbo

    instances of determination and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.83
     exting
    -0.75
     metic
    -0.73
    ò
    -0.72
    senal
    -0.71
    isSpecial
    -0.70
    VILLE
    -0.70
     sqor
    -0.70
    ailability
    -0.68
    ĨĴ
    -0.67
    POSITIVE LOGITS
    az
    0.77
    ke
    0.77
    ipp
    0.74
    ff
    0.73
    £
    0.73
     Modi
    0.72
    iqu
    0.72
    о
    0.70
    hed
    0.70
     Bosh
    0.69
    Activations Density 0.142%

    No Known Activations