© 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. 8-RES-JB
    11. 14277
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology and network capabilities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of different generations of wireless technology, specifically 3G, 4G, and 5G

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ãĤ©
    -0.68
    ific
    -0.61
     ç¥ŀ
    -0.60
    lins
    -0.59
    Recomm
    -0.59
    humane
    -0.58
    esses
    -0.58
    TPPStreamerBot
    -0.57
    ciating
    -0.57
    breeding
    -0.56
    POSITIVE LOGITS
    bps
    1.15
    hz
    0.97
    HS
    0.91
    Hz
    0.73
    II
    0.71
    agonist
    0.70
    OT
    0.70
    TPP
    0.69
    KO
    0.67
    ISA
    0.67
    Activations Density 0.092%

    No Known Activations