© 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. 2951
    Prev
    Next
    INDEX
    Explanations

    numerical measurements denoting size, weight, or capacity

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements related to size and weight

    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
    actionDate
    -0.75
    akeru
    -0.66
    folk
    -0.65
     lapse
    -0.63
    Ô
    -0.60
    last
    -0.57
     Cutter
    -0.56
    furt
    -0.56
    vati
    -0.56
     slump
    -0.55
    POSITIVE LOGITS
     trillion
    1.19
     billion
    1.10
    200
    1.09
     million
    1.07
    500
    1.05
     lakh
    1.01
     hundred
    1.00
     Billion
    1.00
    billion
    1.00
     thousand
    0.97
    Activations Density 0.098%

    No Known Activations