© 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. 1106
    Prev
    Next
    INDEX
    Explanations

    words related to challenges, crisis, and conflicts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social, economic, and environmental issues

    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
     Hond
    -0.70
    ocent
    -0.61
     Cary
    -0.61
     Ack
    -0.60
    alus
    -0.59
     Berm
    -0.59
    flix
    -0.59
     ASA
    -0.58
     pestic
    -0.58
     Gaul
    -0.57
    POSITIVE LOGITS
    </
    0.85
    âĢ
    0.74
     counterpart
    0.74
     counterparts
    0.72
    *,
    0.70
    [/
    0.68
     ().
    0.68
     reputation
    0.67
    mma
    0.67
     moniker
    0.66
    Activations Density 0.617%

    No Known Activations