© 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. 5544
    Prev
    Next
    INDEX
    Explanations

    phrases indicating size, quantity, or degree

    oai_token-act-pair · gpt-3.5-turbo

    assertions about performance relative to expectations

    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
     Britann
    -0.64
    leted
    -0.61
     CRC
    -0.59
     irresistible
    -0.57
     legend
    -0.56
     DRAGON
    -0.55
     gorgeous
    -0.55
     legends
    -0.55
     ROCK
    -0.55
     forged
    -0.54
    POSITIVE LOGITS
     anymore
    1.32
     nor
    1.22
    nor
    1.06
     whatsoever
    0.93
     anywhere
    0.89
    enough
    0.88
     unless
    0.82
    yet
    0.81
     anything
    0.80
     necessarily
    0.79
    Activations Density 0.792%

    No Known Activations