© 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. 20769
    Prev
    Next
    INDEX
    Explanations

    the last names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letters "ri," "ro," and similar letter combinations within words

    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
    ĸļ
    -0.76
    externalActionCode
    -0.64
     timeless
    -0.64
    ĨĴ
    -0.63
     refere
    -0.62
     feder
    -0.62
    ciating
    -0.62
     wards
    -0.61
     newsletters
    -0.61
    matically
    -0.61
    POSITIVE LOGITS
    heim
    0.89
    ÃŃn
    0.86
    vous
    0.85
    essim
    0.82
    agy
    0.79
    wald
    0.78
    gyn
    0.77
    alla
    0.76
    inus
    0.76
    ulin
    0.75
    Activations Density 0.205%

    No Known Activations