© 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. 16945
    Prev
    Next
    INDEX
    Explanations

    contractions ('aren't', 'won't', 'isn't', etc.)

    oai_token-act-pair · gpt-3.5-turbo

    negations or contractions related to the state of being

    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
    anwhile
    -0.86
     enthusi
    -0.83
     destro
    -0.78
     princ
    -0.78
     eleph
    -0.76
     gobl
    -0.76
     newcom
    -0.74
     unnecess
    -0.69
     exha
    -0.69
     metic
    -0.68
    POSITIVE LOGITS
    't
    1.73
    ited
    0.88
    ÃŃ
    0.88
    ´
    0.87
    iting
    0.86
    itely
    0.85
    atically
    0.83
    Dispatch
    0.80
    uts
    0.79
    acio
    0.79
    Activations Density 0.082%

    No Known Activations