© 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. 7-RES-JB
    11. 3054
    Prev
    Next
    INDEX
    Explanations

    the word "lion" with various intensities

    oai_token-act-pair · gpt-3.5-turbo

    references to lions and related big cats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.88
    chell
    -0.87
    lying
    -0.76
    ilk
    -0.73
    ACTION
    -0.72
    matter
    -0.69
    Ñı
    -0.69
    ÑĮ
    -0.68
     McKenna
    -0.67
    Interstitial
    -0.63
    POSITIVE LOGITS
    esses
    1.21
    fish
    1.02
    eye
    1.01
    ess
    1.00
     lions
    0.92
    ous
    0.90
    stal
    0.89
    osaurs
    0.88
    odon
    0.87
    iasis
    0.86
    Activations Density 0.019%

    No Known Activations