© 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. 8778
    Prev
    Next
    INDEX
    Explanations

    compound words with 'ill' as a prefix

    oai_token-act-pair · gpt-3.5-turbo

    phrases associated with negative or unfavorable conditions

    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
    illon
    -0.79
     Sharing
    -0.61
     Forestry
    -0.58
    £ı
    -0.57
     rings
    -0.57
     patrols
    -0.57
    iture
    -0.56
     Publishers
    -0.55
     Nope
    -0.54
     Noir
    -0.54
    POSITIVE LOGITS
    gotten
    1.14
    fitting
    1.02
    informed
    0.97
    defined
    0.95
    equipped
    0.90
    treatment
    0.90
    founded
    0.89
    tim
    0.88
    intent
    0.85
    iquid
    0.84
    Activations Density 0.034%

    No Known Activations