© 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. 10650
    Prev
    Next
    INDEX
    Explanations

    phrases related to drawing conclusions or making final judgments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conclusions or assessments

    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
    tan
    -0.72
    corn
    -0.70
    lease
    -0.69
    enf
    -0.67
    loads
    -0.67
    names
    -0.66
    dimension
    -0.66
    gren
    -0.65
    eni
    -0.64
    isters
    -0.64
    POSITIVE LOGITS
     concluding
    0.78
     unanimously
    0.74
     that
    0.73
     definitively
    0.71
     unequivocally
    0.71
     conclusion
    0.67
     conclude
    0.63
     relying
    0.62
    mand
    0.61
     Sole
    0.61
    Activations Density 0.023%

    No Known Activations