© 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. 19685
    Prev
    Next
    INDEX
    Explanations

    phrases related to public infrastructure projects

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "works" and its variations in different contexts

    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
    SPONSORED
    -0.82
    Cath
    -0.81
     Adin
    -0.68
    ĪĴ
    -0.68
     blockers
    -0.67
     Rohing
    -0.66
    ishops
    -0.66
    OPLE
    -0.64
    wcs
    -0.63
    ACP
    -0.62
    POSITIVE LOGITS
    hops
    1.47
    paces
    1.32
    pace
    1.17
    hirt
    1.12
    heet
    1.07
    hift
    0.92
    peed
    0.87
    afe
    0.87
    flows
    0.87
    creen
    0.86
    Activations Density 0.023%

    No Known Activations