© 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. 11-RES-JB
    11. 21011
    Prev
    Next
    INDEX
    Explanations

    numerical quantities followed by a unit of measurement

    oai_token-act-pair · gpt-3.5-turbo

    quantifications and numeric references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    inventoryQuantity
    -0.63
    ococ
    -0.61
     sooner
    -0.58
    aign
    -0.55
    agate
    -0.51
    liction
    -0.50
    WP
    -0.49
     exting
    -0.48
     alarms
    -0.47
    FH
    -0.47
    POSITIVE LOGITS
     dozen
    1.33
    dozen
    1.27
     200
    1.19
     1000
    1.17
     300
    1.17
     fifty
    1.16
     150
    1.16
     1500
    1.16
     3000
    1.15
     sixty
    1.15
    Activations Density 0.120%

    No Known Activations