© 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. 4-RES-JB
    11. 4807
    Prev
    Next
    INDEX
    Explanations

    unexpected or surprising information in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate surprise or unexpectedness

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

    No Comments

    Negative Logits
    gin
    -0.72
    flight
    -0.70
    tein
    -0.68
    glas
    -0.67
    aily
    -0.67
    trak
    -0.67
    gang
    -0.66
    rity
    -0.66
    allas
    -0.65
    iche
    -0.64
    POSITIVE LOGITS
    ESA
    0.82
    STEM
    0.80
    beit
    0.68
    AppData
    0.64
    Accessory
    0.63
     Remastered
    0.63
    Berry
    0.63
     absent
    0.63
    NESS
    0.62
    TPP
    0.62
    Activations Density 0.012%

    No Known Activations