© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4034
    Prev
    Next
    INDEX
    Explanations

    numeric patterns in a specific format

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of phrases indicating comparisons or contrasts between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     metic
    -0.93
     corrid
    -0.85
     millenn
    -0.83
     mosqu
    -0.83
     Moroc
    -0.83
    Þ
    -0.81
     satell
    -0.78
     reluct
    -0.78
    ò
    -0.76
     unbeliev
    -0.74
    POSITIVE LOGITS
    pmwiki
    0.83
    ones
    0.81
    etime
    0.76
    --+
    0.71
    itch
    0.71
    zo
    0.70
    one
    0.69
    four
    0.68
    percent
    0.67
    _>
    0.65
    Activations Density 0.029%

    No Known Activations