© 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. 10275
    Prev
    Next
    INDEX
    Explanations

    names or terms related to "Ker" with varying degrees of specificity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Ker" and its variations

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

    No Comments

    Negative Logits
    ers
    -0.73
    UME
    -0.70
    ELS
    -0.68
    è£ħ
    -0.67
     Cascade
    -0.63
    ership
    -0.62
     Hogan
    -0.60
    ERS
    -0.60
     Lovecraft
    -0.59
    urst
    -0.59
    POSITIVE LOGITS
    bal
    1.15
    rigan
    1.12
    sei
    0.99
    berus
    0.99
    rors
    0.97
    mit
    0.96
    der
    0.94
    ber
    0.93
    cher
    0.92
    itage
    0.92
    Activations Density 0.075%

    No Known Activations