© 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. 3-RES-JB
    11. 17179
    Prev
    Next
    INDEX
    Explanations

    non-letter characters like symbols and numbers at the end of tokens

    oai_token-act-pair · gpt-3.5-turbo

    the symbol 'âĦ¢' which appears to represent various high activation contexts, possibly indicating focus on significant concepts or themes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    esses
    -0.84
    glers
    -0.80
    */(
    -0.76
    izont
    -0.76
    INTON
    -0.74
    neys
    -0.73
    amus
    -0.71
    utterstock
    -0.69
     marrow
    -0.67
    itionally
    -0.67
    POSITIVE LOGITS
    ternity
    0.79
    âĦ¢
    0.79
    tre
    0.73
    peak
    0.72
    ãĤº
    0.72
    entimes
    0.69
    Ħ¢
    0.69
    CHAT
    0.67
    âĨij
    0.65
    Bet
    0.65
    Activations Density 0.007%

    No Known Activations