© 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. 3-RES-JB
    11. 16798
    Prev
    Next
    INDEX
    Explanations

    verbs related to action or processes

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to legal and financial transactions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    clerosis
    -0.63
    cipled
    -0.62
    issue
    -0.62
    adier
    -0.61
    ansky
    -0.58
    opic
    -0.57
    annis
    -0.56
    esa
    -0.56
    arty
    -0.55
    RESULTS
    -0.55
    POSITIVE LOGITS
    ocument
    0.69
    nesday
    0.67
     subur
    0.61
    ãĤ´ãĥ³
    0.60
     srf
    0.60
    DeliveryDate
    0.60
     by
    0.58
    river
    0.55
     Parenthood
    0.54
     referen
    0.54
    Activations Density 0.650%

    No Known Activations