© 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. 778
    Prev
    Next
    INDEX
    Explanations

    numbers related to quantities or estimates

    oai_token-act-pair · gpt-3.5-turbo

    quantitative estimates and numerical data

    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
    idity
    -0.66
     acquaint
    -0.60
    pb
    -0.59
    iator
    -0.59
     presumption
    -0.59
    opal
    -0.58
     elig
    -0.57
     Awakens
    -0.56
    iat
    -0.56
    perture
    -0.55
    POSITIVE LOGITS
     tens
    1.23
     hundreds
    1.22
    undreds
    1.12
     thousands
    1.09
     trillions
    1.05
     dozens
    1.03
     billions
    1.00
     upwards
    1.00
     millions
    0.96
     decades
    0.94
    Activations Density 0.334%

    No Known Activations