© 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. 10-RES-JB
    11. 13760
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a strong statement or conclusion

    oai_token-act-pair · gpt-3.5-turbo

    punctuation, particularly periods and other sentence-ending markers

    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
    VIDIA
    -0.83
     tremend
    -0.81
    ŃĶ
    -0.77
    ishable
    -0.75
    yip
    -0.73
     enthusi
    -0.73
     elig
    -0.73
    ikuman
    -0.72
     unden
    -0.71
    hesda
    -0.70
    POSITIVE LOGITS
     Though
    1.44
     Initially
    1.44
     According
    1.42
     Since
    1.40
     Although
    1.39
     Despite
    1.37
     Needless
    1.35
     Essentially
    1.34
     During
    1.33
     While
    1.33
    Activations Density 0.352%

    No Known Activations