© 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. 10-RES-JB
    11. 13569
    Prev
    Next
    INDEX
    Explanations

    words related to specific terms, including technical jargon, names, and numerical quantities

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to specific identities, rules, or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PROV
    -0.59
    osaurs
    -0.58
     Copyright
    -0.54
    Pg
    -0.53
    natureconservancy
    -0.51
    Flickr
    -0.50
    halla
    -0.50
    ãĢ
    -0.50
    ::::::::
    -0.50
    ================================================================
    -0.49
    POSITIVE LOGITS
    rique
    0.68
    eers
    0.65
     pregn
    0.59
    alion
    0.57
     rul
    0.57
     skelet
    0.56
    ificate
    0.56
     Cooke
    0.52
    nered
    0.51
     blat
    0.50
    Activations Density 1.530%

    No Known Activations