© 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. 5108
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name "Kara" along with some variations like "Kara<tab>10", "Kara<tab>9", and mentions of "Dylan"

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

    mentions of the name "Kara" or other relevant names 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 @ 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
    ers
    -0.90
    mble
    -0.81
    llah
    -0.81
    cation
    -0.80
    uay
    -0.79
    eq
    -0.79
    lasses
    -0.78
    err
    -0.78
    yg
    -0.77
    xual
    -0.74
    POSITIVE LOGITS
    osure
    0.90
    ose
    0.84
    oke
    0.77
    ocl
    0.75
    uthor
    0.74
    oses
    0.71
    itic
    0.70
    obo
    0.69
    uder
    0.69
    ise
    0.68
    Activations Density 0.269%

    No Known Activations