© 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. 6-RES-JB
    11. 13822
    Prev
    Next
    INDEX
    Explanations

    phrases related to surprising or shocking information

    oai_token-act-pair · gpt-3.5-turbo

    references to surprise or shock directed towards individuals or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disappearing
    -0.62
     elevation
    -0.61
     backups
    -0.59
     ampl
    -0.58
     minus
    -0.58
     mut
    -0.55
     ord
    -0.55
    BuyableInstoreAndOnline
    -0.55
     github
    -0.55
    OPA
    -0.54
    POSITIVE LOGITS
    selves
    0.95
    jah
    0.94
    hematically
    0.84
    DERR
    0.78
    antics
    0.75
     [*
    0.74
     alike
    0.72
     sensibilities
    0.71
    aughs
    0.70
    oppers
    0.70
    Activations Density 0.298%

    No Known Activations