© 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. 8-RES-JB
    11. 12495
    Prev
    Next
    INDEX
    Explanations

    words related to technology or computing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "du" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĨ
    -0.70
    objects
    -0.67
     Conditions
    -0.65
    practice
    -0.64
    skirts
    -0.60
    sburgh
    -0.60
    sburg
    -0.60
    iances
    -0.59
    RESULTS
    -0.58
     Ambro
    -0.57
    POSITIVE LOGITS
    ²¾
    0.96
    cci
    0.94
    pper
    0.93
    gment
    0.91
    cks
    0.91
    ª
    0.86
    llo
    0.86
    nder
    0.84
    elist
    0.83
    pperc
    0.82
    Activations Density 0.019%

    No Known Activations