© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6216
    Prev
    Next
    INDEX
    Explanations

    the word "opener" in the context of events or games

    oai_token-act-pair · gpt-3.5-turbo

    references to sports season openers

    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
    majority
    -0.71
     Hume
    -0.71
    ivan
    -0.66
    hab
    -0.65
    nda
    -0.63
    ivable
    -0.63
    inders
    -0.62
    ordan
    -0.61
    protein
    -0.61
    olution
    -0.60
    POSITIVE LOGITS
     opener
    1.38
    glers
    0.93
    daq
    0.77
     opens
    0.76
    eering
    0.75
    eers
    0.73
    spection
    0.72
     postponed
    0.72
     externalToEVAOnly
    0.71
     showc
    0.69
    Activations Density 0.004%

    No Known Activations