© 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 EvalsExportsAPI 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. 4-RES-JB
    11. 1529
    Prev
    Next
    INDEX
    Explanations

    terms related to a person or entity named "Davis"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated mention of the name "Davis"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥĪ
    -0.74
    emort
    -0.72
    lopp
    -0.71
    ugal
    -0.69
    ikarp
    -0.68
     Seym
    -0.68
     subscript
    -0.68
    awaru
    -0.67
    liest
    -0.67
    bably
    -0.65
    POSITIVE LOGITS
     Davis
    1.06
    Davis
    0.91
     Hanson
    0.90
    essa
    0.87
    ville
    0.80
     Webb
    0.78
    acre
    0.77
    den
    0.76
    pole
    0.75
    mouth
    0.74
    Activations Density 0.011%

    No Known Activations