© 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. 2572
    Prev
    Next
    INDEX
    Explanations

    terms related to historical and scientific discoveries

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

    instances of conjunctions and transitions that indicate relationships or connections between ideas

    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
     myself
    -0.79
     yourselves
    -0.78
     me
    -0.73
     ourselves
    -0.69
     yourself
    -0.65
     my
    -0.64
     us
    -0.63
     Our
    -0.60
     My
    -0.58
     Your
    -0.58
    POSITIVE LOGITS
     teasp
    0.96
     practition
    0.95
     pione
    0.91
    ö
    0.85
    ù
    0.85
    č
    0.85
    ę
    0.85
    À
    0.85
    embedreportprint
    0.84
    ė
    0.84
    Activations Density 0.333%

    No Known Activations