© 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. 6-RES-JB
    11. 9380
    Prev
    Next
    INDEX
    Explanations

    verbs related to sudden changes or realizations

    oai_token-act-pair · gpt-3.5-turbo

    verbs that indicate a change in state or condition

    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
    arta
    -0.66
    sel
    -0.65
     Parables
    -0.65
    itable
    -0.64
     congratulated
    -0.64
     Portable
    -0.64
    ledge
    -0.62
     towed
    -0.60
     qualified
    -0.59
     alternatives
    -0.59
    POSITIVE LOGITS
     downhill
    0.84
    IER
    0.80
     exponentially
    0.80
     explos
    0.78
    icter
    0.76
     une
    0.73
     spontaneously
    0.72
     downward
    0.72
     downwards
    0.68
     anew
    0.68
    Activations Density 0.266%

    No Known Activations