© 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. 4950
    Prev
    Next
    INDEX
    Explanations

    biographical information and personal experiences

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

    expressions and phrases related to emotional experiences and social interactions

    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
    audi
    -0.85
    sections
    -0.83
    pps
    -0.82
    ©¶æ¥µ
    -0.81
    osher
    -0.81
    代
    -0.81
    EStream
    -0.79
    isites
    -0.78
    sites
    -0.78
    levant
    -0.77
    POSITIVE LOGITS
     frustration
    1.46
     desperation
    1.45
     uncertainty
    1.42
     disappointment
    1.41
     confusion
    1.41
     resentment
    1.40
     insecurity
    1.39
     betrayal
    1.39
     despair
    1.36
     sadness
    1.33
    Activations Density 0.243%

    No Known Activations