© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18818
    Prev
    Next
    INDEX
    Explanations

    words with the suffix "-oen"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological or medical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     goodbye
    -0.70
    lessness
    -0.68
    reys
    -0.67
    HAEL
    -0.66
    dos
    -0.64
    lessly
    -0.64
     Attention
    -0.62
    rush
    -0.62
     Independence
    -0.61
    meet
    -0.61
    POSITIVE LOGITS
    velop
    1.17
    ffect
    1.03
    vironment
    0.96
    omed
    0.95
    uclear
    0.93
    chn
    0.92
    cies
    0.91
    otyp
    0.91
    oming
    0.90
    zyme
    0.90
    Activations Density 0.125%

    No Known Activations