© 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. 17466
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mart" with varying levels of importance or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Mart" or variations of it

    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
     conce
    -0.69
    clips
    -0.68
     eminent
    -0.66
    ught
    -0.61
    QUEST
    -0.61
    WAYS
    -0.60
    glers
    -0.60
     Norn
    -0.60
    UTH
    -0.60
     fluoride
    -0.59
    POSITIVE LOGITS
    inez
    1.43
    yrs
    1.36
    ijn
    1.30
    yr
    1.20
    ial
    1.18
    inelli
    1.17
    ians
    1.14
    ially
    1.13
    ini
    1.13
    inal
    1.11
    Activations Density 0.022%

    No Known Activations