© 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 EvalsExportsinterp-engineNEWAPI 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. 1091
    Prev
    Next
    INDEX
    Explanations

    individual marks or indicators within a context

    oai_token-act-pair · gpt-3.5-turbo

    references to scoring or evaluation metrics

    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
    ILLE
    -0.93
    abama
    -0.71
    anooga
    -0.69
    ettel
    -0.68
    agan
    -0.68
    rouch
    -0.66
    imation
    -0.66
    odka
    -0.65
     Kut
    -0.64
     brut
    -0.61
    POSITIVE LOGITS
    manship
    1.50
    downs
    1.07
    down
    1.03
    eters
    0.97
     Twain
    0.95
    emark
    0.93
    ups
    0.88
    posts
    0.87
    lights
    0.84
    eting
    0.83
    Activations Density 0.030%

    No Known Activations