© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18714
    Prev
    Next
    INDEX
    Explanations

    numbers and numerical expressions

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements

    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
    vice
    -0.58
    rology
    -0.56
     spont
    -0.55
     exchange
    -0.55
    opter
    -0.54
     equilibrium
    -0.53
     reperc
    -0.53
    lication
    -0.52
    foundation
    -0.52
    theme
    -0.52
    POSITIVE LOGITS
     miles
    1.23
     kilometers
    1.18
    years
    1.17
     inches
    1.14
     years
    1.14
    inches
    1.13
     kilometres
    1.09
     months
    1.06
    months
    1.02
     centimeters
    1.01
    Activations Density 0.115%

    No Known Activations