© 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. 9-RES-JB
    11. 10235
    Prev
    Next
    INDEX
    Explanations

    adjectives or adverbs indicating a comparative degree

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors that convey precision or quality in various contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ĺħ
    -0.71
     teasp
    -0.65
    atel
    -0.63
    acl
    -0.60
     entirety
    -0.60
    ãĤ´ãĥ³
    -0.59
    owell
    -0.59
    CHAT
    -0.56
    FORE
    -0.54
    irrel
    -0.53
    POSITIVE LOGITS
     than
    2.00
    than
    1.68
     Than
    1.45
    worldly
    0.82
    iating
    0.79
    iated
    0.73
    erous
    0.71
    ially
    0.70
    romeda
    0.68
     sounding
    0.68
    Activations Density 0.191%

    No Known Activations