© 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. 9-RES-JB
    11. 11695
    Prev
    Next
    INDEX
    Explanations

    entities related to families

    oai_token-act-pair · gpt-3.5-turbo

    references to specific families

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psey
    -1.08
    jriwal
    -0.85
    isexual
    -0.82
    pport
    -0.81
    alys
    -0.81
    uesday
    -0.81
     guiActiveUn
    -0.76
    umbn
    -0.76
    ulhu
    -0.74
    isconsin
    -0.73
    POSITIVE LOGITS
     dynasty
    1.03
     patriarch
    1.00
     tree
    0.86
     Tree
    0.83
     heirs
    0.82
     fortune
    0.81
     saga
    0.80
     inherit
    0.78
     mansion
    0.77
     crest
    0.76
    Activations Density 0.127%

    No Known Activations