© 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. 2523
    Prev
    Next
    INDEX
    Explanations

    expressions of confidence or excitement

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    sentences expressing state of being or feelings

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ãĥīãĥ©
    -0.69
    ruciating
    -0.66
    vernment
    -0.65
    vertisement
    -0.63
    SPONSORED
    -0.61
    č
    -0.60
    obo
    -0.60
    ę
    -0.60
    ù
    -0.60
    Ď
    -0.60
    POSITIVE LOGITS
     excited
    1.02
     glad
    0.94
     thrilled
    0.93
     stoked
    0.92
     definitely
    0.92
     hoping
    0.91
     thankful
    0.88
     fortunate
    0.86
     loving
    0.84
     confident
    0.84
    Activations Density 0.184%

    No Known Activations