© 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. 10-RES-JB
    11. 20659
    Prev
    Next
    INDEX
    Explanations

    specific instances or scenarios related to a general statement or subject

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize a significant number or quantity

    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
    venants
    -0.73
    ledged
    -0.73
    marks
    -0.69
    println
    -0.68
    Domin
    -0.67
    amaru
    -0.66
    onis
    -0.64
    ragon
    -0.62
    pred
    -0.61
    mosp
    -0.58
    POSITIVE LOGITS
     reason
    1.80
     purpose
    1.56
     sake
    1.56
     reasons
    1.45
     purposes
    1.45
     Reason
    1.03
     occasion
    0.99
     Reasons
    0.99
     matter
    0.96
    ummies
    0.85
    Activations Density 0.061%

    No Known Activations