© 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. 16505
    Prev
    Next
    INDEX
    Explanations

    numerical figures in a specific range

    oai_token-act-pair · gpt-3.5-turbo

    numerical values associated with monetary and measurement contexts

    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
    atem
    -0.62
    DIS
    -0.60
    ↵Âł
    -0.58
     Gast
    -0.57
    ":"/
    -0.57
     condem
    -0.57
     fors
    -0.56
     withd
    -0.56
     confir
    -0.56
     neighb
    -0.56
    POSITIVE LOGITS
    000
    1.05
     thousand
    1.01
    0000
    0.95
     lakh
    0.91
    0002
    0.90
    00000
    0.83
    001
    0.82
     000
    0.81
    500
    0.79
     million
    0.77
    Activations Density 0.069%

    No Known Activations