© 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. 11-RES-JB
    11. 24
    Prev
    Next
    INDEX
    Explanations

    personal opinions and reflections

    oai_token-act-pair · gpt-3.5-turbo

    phrases and words indicative of personal reflection or emotional assessment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onnaissance
    -0.62
    igent
    -0.61
    xon
    -0.61
    often
    -0.58
     metic
    -0.58
    ropy
    -0.57
    azard
    -0.57
    ometimes
    -0.56
    xtap
    -0.56
    etooth
    -0.56
    POSITIVE LOGITS
    âĢ
    1.13
     âĢ
    0.89
    ?!"
    0.84
    ãĢ
    0.83
     toget
    0.78
    ··
    0.78
    [/
    0.75
     gonna
    0.75
    ????????
    0.74
     EVER
    0.74
    Activations Density 0.756%

    No Known Activations