© 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. 1-RES-JB
    11. 2376
    Prev
    Next
    INDEX
    Explanations

    contractions of "ain't"

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions and phrases indicating disagreement or denial

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.68
    Impl
    -0.66
     ItemLevel
    -0.64
    ":["
    -0.63
    assies
    -0.63
    antom
    -0.63
    Closure
    -0.63
    entric
    -0.61
     Destination
    -0.61
    âĹı
    -0.61
    POSITIVE LOGITS
     ain
    1.13
    't
    0.95
    thouse
    0.87
     gonna
    0.86
    gin
    0.85
     gotta
    0.79
    strument
    0.79
    \\\\\\\\
    0.78
    ppo
    0.78
    terness
    0.73
    Activations Density 0.006%

    No Known Activations