© 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. 10100
    Prev
    Next
    INDEX
    Explanations

    large numbers referencing quantities like studies, people, and measurements

    oai_token-act-pair · gpt-3.5-turbo

    mentions of large numerical quantities, particularly in the context of studies or 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
     matt
    -0.63
     behav
    -0.59
     Goodwin
    -0.54
     jo
    -0.53
     bothered
    -0.53
    ↵Âł
    -0.52
     pains
    -0.52
     nab
    -0.51
     offender
    -0.51
     HC
    -0.51
    POSITIVE LOGITS
    000
    1.67
    500
    1.38
    700
    1.33
    800
    1.33
    600
    1.29
    400
    1.25
    300
    1.24
    200
    1.22
    900
    1.19
    dozen
    1.12
    Activations Density 0.058%

    No Known Activations