© 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. 7226
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing surprise or astonishment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or unexpectedness

    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
    ioxide
    -0.68
    ngth
    -0.66
     manned
    -0.66
     bonded
    -0.66
     downed
    -0.64
     inhabited
    -0.60
    doors
    -0.60
     blender
    -0.59
     rou
    -0.59
    annabin
    -0.59
    POSITIVE LOGITS
     considering
    1.23
     because
    0.94
     given
    0.83
     since
    0.80
     enough
    0.76
     insofar
    0.76
    soType
    0.75
    because
    0.74
     nonetheless
    0.74
    imaru
    0.74
    Activations Density 0.202%

    No Known Activations