© 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. 1-RES-JB
    11. 20284
    Prev
    Next
    INDEX
    Explanations

    terms related to physical locations or events

    oai_token-act-pair · gpt-3.5-turbo

    terms related to quantitative measurements and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.53
    ĻĤ
    -0.52
     COUN
    -0.52
     largeDownload
    -0.51
    IDENT
    -0.50
     CLSID
    -0.50
     SHALL
    -0.49
    Ĥİ
    -0.49
     whe
    -0.49
     distinctive
    -0.48
    POSITIVE LOGITS
    aires
    0.69
    wagen
    0.68
    istan
    0.68
    icut
    0.66
    edIn
    0.65
    ople
    0.63
    atics
    0.63
    atl
    0.61
    idepress
    0.61
    uly
    0.60
    Activations Density 1.416%

    No Known Activations