© 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. 7-RES-JB
    11. 20854
    Prev
    Next
    INDEX
    Explanations

    phrases related to a unique or significant event happening for the first time

    oai_token-act-pair · gpt-3.5-turbo

    references to "first" occasions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maps
    -0.71
     Buildings
    -0.66
    riber
    -0.63
    love
    -0.63
    queue
    -0.63
    */(
    -0.63
    loving
    -0.62
    ractor
    -0.62
    apons
    -0.62
    jon
    -0.61
    POSITIVE LOGITS
     installment
    0.93
     indication
    0.91
     foray
    0.91
     casualty
    0.78
     attempt
    0.77
     hurdle
    0.77
    ever
    0.75
     omission
    0.74
     chance
    0.74
     culmination
    0.74
    Activations Density 0.097%

    No Known Activations