© 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. 15594
    Prev
    Next
    INDEX
    Explanations

    statements made by spokespersons or individuals in a formal context

    oai_token-act-pair · gpt-3.5-turbo

    quotations or statements made by individuals

    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
    pee
    -0.80
    hook
    -0.79
    ILA
    -0.78
    colored
    -0.78
    hack
    -0.73
    caliber
    -0.72
    tumblr
    -0.72
    ize
    -0.71
    Favorite
    -0.71
    ANA
    -0.70
    POSITIVE LOGITS
     whilst
    1.03
     apologised
    1.01
     RAF
    0.96
     organisers
    0.96
     afterwards
    0.95
     £
    0.92
     Britons
    0.92
     Australians
    0.91
     recogn
    0.91
     criticised
    0.88
    Activations Density 0.185%

    No Known Activations