© 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. 12-RES-JB
    11. 4736
    Prev
    Next
    INDEX
    Explanations

    food and brand names with particular enthusiasm

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    specific names or terms that are associated with notable individuals or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inic
    -0.71
     coh
    -0.64
     widow
    -0.61
    yle
    -0.61
    ays
    -0.61
     lar
    -0.61
     moons
    -0.61
    eny
    -0.61
    iana
    -0.61
    inating
    -0.59
    POSITIVE LOGITS
    SPONSORED
    0.77
    ãĥ¼ãĤ¯
    0.73
     Couch
    0.72
    cale
    0.67
    alty
    0.67
    gdala
    0.66
    Limit
    0.66
    ----------
    0.65
    Ag
    0.65
     Flesh
    0.64
    Activations Density 0.143%

    No Known Activations