© 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. 10-RES-JB
    11. 4926
    Prev
    Next
    INDEX
    Explanations

    sentences discussing events or incidents

    oai_token-act-pair · gpt-3.5-turbo

    sentence endings and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charact
    -0.90
     extinct
    -0.78
     cellar
    -0.77
     volunte
    -0.73
     defin
    -0.73
     pudding
    -0.73
     fishes
    -0.72
     regenerate
    -0.71
     strugg
    -0.70
     regener
    -0.70
    POSITIVE LOGITS
     Shortly
    1.53
     Later
    1.37
     Today
    1.33
     Immediately
    1.32
     Months
    1.31
     Afterwards
    1.30
     Since
    1.29
     Soon
    1.29
     Previously
    1.27
     Now
    1.25
    Activations Density 0.410%

    No Known Activations