© 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. 1209
    Prev
    Next
    INDEX
    Explanations

    descriptions of products or experiences

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that denote quality, value, and enhancement

    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
    )?
    -0.78
    ?).
    -0.71
    .).
    -0.70
     attRot
    -0.66
    apo
    -0.66
    SPONSORED
    -0.65
    Attempt
    -0.62
     theirs
    -0.61
     ).
    -0.60
     afterwards
    -0.60
    POSITIVE LOGITS
     timeless
    0.80
     versatility
    0.76
     concept
    0.74
     concepts
    0.74
     modular
    0.72
     synerg
    0.70
     creativity
    0.70
     innovative
    0.69
     classic
    0.69
     seamlessly
    0.69
    Activations Density 1.189%

    No Known Activations