© 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. 7-RES-JB
    11. 21197
    Prev
    Next
    INDEX
    Explanations

    references to invalid email addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    invalid or incorrect email addresses

    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
    thood
    -0.81
    laus
    -0.79
    abouts
    -0.73
    bett
    -0.72
    rat
    -0.70
    fam
    -0.69
    steen
    -0.68
    olutely
    -0.68
    roo
    -0.68
    esses
    -0.67
    POSITIVE LOGITS
     address
    0.86
     sender
    0.86
     inbox
    0.80
     addresses
    0.75
     email
    0.74
     addr
    0.72
     alerts
    0.72
    ä¿
    0.72
     password
    0.70
     invitation
    0.69
    Activations Density 0.015%

    No Known Activations