© 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. 9-RES-JB
    11. 19542
    Prev
    Next
    INDEX
    Explanations

    percentage numbers and rates

    oai_token-act-pair · gpt-3.5-turbo

    numerical growth rates and statistics related to financial or economic data

    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
    agher
    -0.66
    çīĪ
    -0.61
    osen
    -0.61
     salvage
    -0.59
    perture
    -0.59
    hid
    -0.59
    achable
    -0.59
    pard
    -0.58
    ottesville
    -0.58
     hangs
    -0.58
    POSITIVE LOGITS
     exponential
    1.06
     faster
    0.97
     pace
    0.94
     exponentially
    0.91
     leaps
    0.91
     accelerating
    0.90
     rate
    0.90
     slower
    0.90
     steadily
    0.86
     accelerated
    0.86
    Activations Density 0.260%

    No Known Activations