© 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. 2-RES-JB
    11. 12732
    Prev
    Next
    INDEX
    Explanations

    phrases related to TV show schedules, particularly mentioning "SportsCenter"

    oai_token-act-pair · gpt-3.5-turbo

    references to central sports events or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Enhance
    -0.75
    imar
    -0.73
    obin
    -0.72
    ento
    -0.70
    yd
    -0.68
    ategory
    -0.67
    AAAA
    -0.64
    urb
    -0.63
     conclud
    -0.63
    ortun
    -0.63
    POSITIVE LOGITS
    EngineDebug
    0.69
     Ogre
    0.67
     encamp
    0.64
     knights
    0.63
     Shinra
    0.62
     Ghostbusters
    0.62
    ãĤ¢ãĥ«
    0.60
     anim
    0.58
     mim
    0.58
     camps
    0.57
    Activations Density 0.001%

    No Known Activations