© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-RES-JB
    11. 5044
    Prev
    Next
    INDEX
    Explanations

    punctuation marks at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     policymakers
    -0.84
    escription
    -0.84
    ciplinary
    -0.81
    ilitation
    -0.79
    merce
    -0.78
     withd
    -0.77
    orescence
    -0.77
    everal
    -0.76
    ¥ŀ
    -0.76
     endeav
    -0.74
    POSITIVE LOGITS
     Anyway
    1.80
     Seriously
    1.57
     ;)
    1.55
     Yeah
    1.46
     Oops
    1.45
     Yep
    1.43
    Anyway
    1.43
     Sorry
    1.38
     ðŁĻĤ
    1.34
     Hmm
    1.33
    Activations Density 0.550%

    No Known Activations