© 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. 18410
    Prev
    Next
    INDEX
    Explanations

    instances where characters are acting or moving

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly commas

    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
    regate
    -0.92
    Commerce
    -0.76
    Nation
    -0.75
    ablishment
    -0.74
    Availability
    -0.74
    isi
    -0.74
    FER
    -0.72
    redit
    -0.72
    mite
    -0.71
    Individual
    -0.71
    POSITIVE LOGITS
     blinking
    1.09
     clutching
    1.07
     grinning
    1.06
     waving
    1.01
     leaning
    1.01
     nodding
    1.01
     wiping
    1.01
     staring
    1.00
     letting
    0.98
     gest
    0.97
    Activations Density 0.194%

    No Known Activations