© 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. 10-RES-JB
    11. 16689
    Prev
    Next
    INDEX
    Explanations

    names of newspapers and companies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that mention sources or authors in reporting

    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
     ripple
    -0.57
     sul
    -0.55
     anecd
    -0.54
     fallout
    -0.54
     shrug
    -0.53
     anyways
    -0.53
     sigh
    -0.52
    FontSize
    -0.52
     flush
    -0.51
     goose
    -0.51
    POSITIVE LOGITS
    anium
    0.69
    AppData
    0.68
    iscover
    0.63
    agen
    0.62
    Publisher
    0.60
    és
    0.60
    vern
    0.59
    nex
    0.59
    psey
    0.58
    Appearances
    0.58
    Activations Density 0.441%

    No Known Activations