© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10363
    Prev
    Next
    INDEX
    Explanations

    words related to processes or mechanisms involving actions or events

    oai_token-act-pair · gpt-3.5-turbo

    words related to locations and conditions in descriptions

    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
    swick
    -0.86
    soType
    -0.82
    inventoryQuantity
    -0.78
    daq
    -0.76
    âĹ¼
    -0.74
    EStream
    -0.74
    still
    -0.74
    Champ
    -0.72
    displayText
    -0.68
    andre
    -0.68
    POSITIVE LOGITS
     individuals
    0.93
     disparate
    0.93
     successive
    0.93
     everyone
    0.87
     each
    0.86
     every
    0.84
     nodes
    0.84
     whoever
    0.83
     wealthy
    0.83
     everybody
    0.82
    Activations Density 0.454%

    No Known Activations