© 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. 9-RES-JB
    11. 4162
    Prev
    Next
    INDEX
    Explanations

    phrases related to things that stand out or are unique

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating something that is distinctive or prominent

    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
    elf
    -0.91
    ummer
    -0.74
     lockout
    -0.67
     confir
    -0.66
     typo
    -0.64
    itamin
    -0.64
    ettlement
    -0.62
    ourse
    -0.61
    ternal
    -0.61
    ynchron
    -0.60
    POSITIVE LOGITS
     amongst
    1.08
     among
    0.94
     prominently
    0.85
     conspic
    0.83
     brightly
    0.81
    box
    0.77
    ocl
    0.76
     visually
    0.75
     Flavoring
    0.74
    comings
    0.73
    Activations Density 0.043%

    No Known Activations