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

    Neuronpedia

    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. 11-RES-JB
    11. 20686
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Ye" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Ye," suggesting a focus on a particular individual or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĨ
    -0.72
    INESS
    -0.66
    tracking
    -0.64
    icut
    -0.63
    dimension
    -0.62
    ITY
    -0.61
     impunity
    -0.61
    DOWN
    -0.60
    tion
    -0.58
    nature
    -0.58
    POSITIVE LOGITS
    oman
    1.25
    ldon
    1.03
    hovah
    1.01
    lde
    0.98
    ats
    0.96
    ager
    0.93
    lda
    0.93
    ast
    0.93
    orge
    0.91
    pez
    0.90
    Activations Density 0.026%

    No Known Activations