© 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. 3659
    Prev
    Next
    INDEX
    Explanations

    titles or mentions of blogs

    oai_token-act-pair · gpt-3.5-turbo

    references to blogs

    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
    aved
    -0.70
    affe
    -0.70
     vain
    -0.68
    IELD
    -0.66
     fem
    -0.65
     prospect
    -0.65
    terday
    -0.63
    cephal
    -0.62
     compr
    -0.61
     dial
    -0.61
    POSITIVE LOGITS
    ging
    1.70
    gers
    1.47
    ger
    1.46
    ged
    1.37
    ues
    1.02
    glers
    1.01
    gment
    0.93
    lio
    0.92
    gement
    0.91
    ges
    0.91
    Activations Density 0.023%

    No Known Activations