© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24165
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names or terms possibly related to a specific place or person named "Kan"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kan" and related names

    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
    ongyang
    -0.83
    suit
    -0.76
    ignty
    -0.73
    yers
    -0.72
    finger
    -0.71
     Seym
    -0.69
    suits
    -0.69
    Skill
    -0.68
    hovah
    -0.65
    lyn
    -0.64
    POSITIVE LOGITS
    igans
    1.24
    ufact
    1.09
    thal
    1.06
    atural
    1.03
    ovember
    1.01
    ovich
    1.01
    omics
    1.01
    igan
    0.98
    ews
    0.98
    istic
    0.93
    Activations Density 0.102%

    No Known Activations