© 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. 19742
    Prev
    Next
    INDEX
    Explanations

    words describing small or slight differences or intensities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express mild dissatisfaction or critique about something

    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
    idth
    -0.99
    psons
    -0.89
     Flavoring
    -0.88
    itivity
    -0.87
    ulkan
    -0.87
    itizen
    -0.83
    hire
    -0.83
    enaries
    -0.82
    iership
    -0.82
    ocity
    -0.80
    POSITIVE LOGITS
     confusing
    1.16
     tricky
    1.14
     pricey
    1.12
     scary
    1.11
     awkward
    1.10
     misleading
    1.07
     disappointing
    1.07
     confused
    1.06
     daunting
    1.05
     intimidating
    1.04
    Activations Density 0.046%

    No Known Activations