© 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. 4-RES-JB
    11. 20167
    Prev
    Next
    INDEX
    Explanations

    the keyword "Barton"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific legislative figure or bill related to poker

    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
     pointer
    -0.78
    anmar
    -0.76
     reactive
    -0.73
    undai
    -0.72
    uli
    -0.71
     reluct
    -0.69
     jaws
    -0.69
     plun
    -0.69
     digits
    -0.67
    otiation
    -0.67
    POSITIVE LOGITS
    age
    1.06
    ages
    1.04
    reath
    0.88
    agher
    0.78
    AGE
    0.77
    aged
    0.76
    stown
    0.75
    AGES
    0.74
    aging
    0.72
    ishing
    0.72
    Activations Density 0.018%

    No Known Activations