© 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. 24197
    Prev
    Next
    INDEX
    Explanations

    phrases indicating legal actions and decisions

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     dips
    -0.90
     worsh
    -0.79
    amins
    -0.78
     scenery
    -0.78
    escent
    -0.78
     lifestyle
    -0.78
     charms
    -0.78
     fascination
    -0.78
    isable
    -0.77
    yip
    -0.77
    POSITIVE LOGITS
     Instead
    1.30
     Ultimately
    1.27
     Nonetheless
    1.24
     Nevertheless
    1.23
     However
    1.18
     Consequently
    1.12
     Specifically
    1.10
     Therefore
    1.10
     Accordingly
    1.10
     Moreover
    1.09
    Activations Density 0.589%

    No Known Activations