© 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. 13597
    Prev
    Next
    INDEX
    Explanations

    phrases indicating exceptions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing exceptions or limitations

    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
     hoop
    -0.67
     merry
    -0.63
    onew
    -0.63
    anners
    -0.62
     hurry
    -0.59
    ocratic
    -0.59
    ocrats
    -0.58
     passers
    -0.58
    rity
    -0.58
     glide
    -0.58
    POSITIVE LOGITS
     LIMITED
    0.93
     limited
    0.86
    excluding
    0.81
     limitation
    0.79
     excluding
    0.76
     excluded
    0.73
     excludes
    0.71
    minus
    0.71
    exclusive
    0.70
    including
    0.70
    Activations Density 0.102%

    No Known Activations