© 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. 10202
    Prev
    Next
    INDEX
    Explanations

    text related to financial transactions or figures with specific formatting

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms

    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
     Hancock
    -0.80
    shr
    -0.79
     Hus
    -0.77
     sus
    -0.76
    bush
    -0.76
     Saras
    -0.75
     spons
    -0.74
    nos
    -0.74
     Seraph
    -0.73
     Sonny
    -0.73
    POSITIVE LOGITS
    et
    1.58
    ET
    1.34
    ett
    1.32
    ets
    1.31
    ete
    1.28
    ette
    1.25
    ét
    1.20
    etta
    1.16
    etting
    1.15
    ETS
    1.13
    Activations Density 0.214%

    No Known Activations