© 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. 8-RES-JB
    11. 23722
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to ecology and ecologists

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ecology and environmental issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Colt
    -0.75
    downs
    -0.75
    MENTS
    -0.73
     gown
    -0.70
     Alleg
    -0.67
    down
    -0.67
    rawdownloadcloneembedreportprint
    -0.65
    ++++++++++++++++
    -0.63
    ounge
    -0.62
     Mandal
    -0.62
    POSITIVE LOGITS
    uador
    1.27
    ologically
    1.10
    lectic
    1.07
    umen
    1.06
    stasy
    1.04
    yssey
    1.02
    entric
    0.98
    ocide
    0.92
    redits
    0.92
    ologists
    0.91
    Activations Density 0.037%

    No Known Activations