© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7481
    Prev
    Next
    INDEX
    Explanations

    phrases related to companies, industries, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    names of companies and organizations

    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
    istically
    -0.88
    liest
    -0.84
    rette
    -0.75
    swer
    -0.71
    zens
    -0.71
    aneously
    -0.69
    less
    -0.68
    otos
    -0.67
    elope
    -0.66
    lled
    -0.65
    POSITIVE LOGITS
    '
    1.83
    pace
    1.40
    hips
    1.36
    hip
    1.34
    ystem
    1.31
    ']
    1.30
    '-
    1.27
    mith
    1.25
    peed
    1.25
    hops
    1.24
    Activations Density 0.365%

    No Known Activations