© 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. 702
    Prev
    Next
    INDEX
    Explanations

    numbers and related mathematical operations

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences or values

    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
    termin
    -0.70
    killed
    -0.70
    orc
    -0.69
    lethal
    -0.68
    hell
    -0.67
    phe
    -0.67
    Cro
    -0.65
    Buzz
    -0.64
    ones
    -0.63
    Sov
    -0.63
    POSITIVE LOGITS
     <!--
    0.92
     ¯
    0.87
     =================================================================
    0.84
     Flavoring
    0.79
     Submit
    0.77
     NOTICE
    0.76
     Next
    0.76
     :=
    0.76
     âĸ
    0.73
     TEAM
    0.73
    Activations Density 0.016%

    No Known Activations