© 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. 9-RES-JB
    11. 22816
    Prev
    Next
    INDEX
    Explanations

    questions asking for preferences or choices among options

    oai_token-act-pair · gpt-3.5-turbo

    questions that inquire about preferences or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ursions
    -0.93
     outreach
    -0.84
     atten
    -0.79
     interf
    -0.79
     resumed
    -0.77
     unauthorized
    -0.77
     reconnect
    -0.76
     repairs
    -0.75
     halted
    -0.75
     setbacks
    -0.73
    POSITIVE LOGITS
     Choose
    1.09
     Choice
    1.04
     Either
    0.99
     Probably
    0.99
     whichever
    0.97
     Winner
    0.93
     Personally
    0.93
    Winner
    0.92
     Whoever
    0.91
    ichever
    0.91
    Activations Density 0.539%

    No Known Activations