© 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. 6-RES-JB
    11. 7769
    Prev
    Next
    INDEX
    Explanations

    verbs indicating action or possibility

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to significant issues or dilemmas in society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.62
     Vaugh
    -0.59
     secretaries
    -0.56
     Kardash
    -0.54
    Aud
    -0.52
    anwhile
    -0.52
     taxp
    -0.47
     fitt
    -0.47
    enegger
    -0.47
     sidx
    -0.47
    POSITIVE LOGITS
    \">
    0.57
    olina
    0.56
    olin
    0.54
    acular
    0.52
    Joined
    0.51
    rogens
    0.50
    mite
    0.50
    aves
    0.48
    SourceFile
    0.48
     >>>
    0.48
    Activations Density 0.654%

    No Known Activations