© 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. 11-RES-JB
    11. 1595
    Prev
    Next
    INDEX
    Explanations

    phrases describing capacity, ability, or behavior

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interested
    -0.75
    pak
    -0.67
     Bringing
    -0.65
    eem
    -0.63
    iling
    -0.63
     Speaking
    -0.62
    ught
    -0.62
    undown
    -0.61
     IMAGES
    -0.61
    ¨
    -0.61
    POSITIVE LOGITS
     mastered
    1.12
     tended
    1.06
     difficulty
    1.04
     trouble
    0.99
     fewer
    0.98
     evolved
    0.96
     ample
    0.96
     been
    0.94
     opted
    0.93
     resorted
    0.93
    Activations Density 0.246%

    No Known Activations