© 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. 14480
    Prev
    Next
    INDEX
    Explanations

    names associated with the term "Kara"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Sara" or variations of it in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ername
    -0.83
    elman
    -0.72
    ership
    -0.71
    ers
    -0.70
    etsk
    -0.67
    rid
    -0.67
    lahoma
    -0.67
    matter
    -0.66
     Gutenberg
    -0.66
    erm
    -0.65
    POSITIVE LOGITS
    vel
    0.98
    uder
    0.89
    uders
    0.86
    oke
    0.84
    uthor
    0.84
    ibaba
    0.81
    ishi
    0.79
    itton
    0.79
    itic
    0.78
     Haj
    0.77
    Activations Density 0.054%

    No Known Activations