© 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. 8-RES-JB
    11. 17736
    Prev
    Next
    INDEX
    Explanations

    questions starting with "why" and "why isn't"

    oai_token-act-pair · gpt-3.5-turbo

    negative contractions used in rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urst
    -0.84
    isers
    -0.70
    fter
    -0.65
    iser
    -0.65
    zer
    -0.64
     Intent
    -0.64
     understatement
    -0.64
     Invalid
    -0.62
     Operator
    -0.61
    oric
    -0.61
    POSITIVE LOGITS
    itia
    0.75
    hin
    0.71
     prosecute
    0.69
     assimil
    0.69
    ippi
    0.67
    amus
    0.66
     mention
    0.66
     vacc
    0.63
     nailed
    0.63
     promptly
    0.63
    Activations Density 0.197%

    No Known Activations