© 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. 9627
    Prev
    Next
    INDEX
    Explanations

    elements related to email subscriptions or newsletters

    oai_token-act-pair · gpt-3.5-turbo
    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
     mole
    -0.69
    eur
    -0.68
     reformed
    -0.62
     sed
    -0.60
     Galile
    -0.59
     Lob
    -0.58
    Dialogue
    -0.58
     Hav
    -0.55
    jury
    -0.55
     tal
    -0.54
    POSITIVE LOGITS
    isode
    0.81
     newsletters
    0.75
    é¾įå¥ij士
    0.71
     inbox
    0.71
    insula
    0.71
    ertodd
    0.70
    idth
    0.70
    psey
    0.69
    aceutical
    0.69
    essage
    0.68
    Activations Density 0.011%

    No Known Activations