© 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. 11-RES-JB
    11. 2322
    Prev
    Next
    INDEX
    Explanations

    words related to technology and technical terms, like specific software or devices

    oai_token-act-pair · gpt-3.5-turbo

    specific product names or technical terms related to technology or electronics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oun
    -0.83
    ©¶æ
    -0.83
     eleph
    -0.81
     conclud
    -0.78
     tremend
    -0.76
     accomp
    -0.76
    Þ
    -0.74
     confir
    -0.73
     hemor
    -0.70
     bureaucr
    -0.69
    POSITIVE LOGITS
    aceae
    0.97
    ipedia
    0.91
    atron
    0.89
    atown
    0.89
    geist
    0.89
    ician
    0.88
    agate
    0.88
    gettable
    0.88
    ecast
    0.86
    aband
    0.86
    Activations Density 0.167%

    No Known Activations