© 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. 1-RES-JB
    11. 787
    Prev
    Next
    INDEX
    Explanations

    references to people with the name "Ke" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ke," likely indicating a focus on a specific individual or related mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.73
    rition
    -0.72
     guiActiveUnfocused
    -0.72
    sburgh
    -0.70
    IONS
    -0.69
    ropolitan
    -0.68
    rations
    -0.66
    ION
    -0.66
    spring
    -0.65
     reconciliation
    -0.65
    POSITIVE LOGITS
    Ke
    1.22
     Ke
    1.10
    SPA
    0.95
    cker
    0.95
    zie
    0.93
    ptic
    0.93
    eling
    0.92
    gg
    0.90
    lem
    0.89
    gan
    0.88
    Activations Density 0.005%

    No Known Activations