© 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. 17128
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to markup, particularly HTML markup

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to "mark" or names associated with it

    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
    enegger
    -0.77
    anchester
    -0.72
    rities
    -0.69
    Tea
    -0.66
    æĢ
    -0.63
    ttp
    -0.63
    姫
    -0.61
    nces
    -0.61
    SPONSORED
    -0.59
    serving
    -0.59
    POSITIVE LOGITS
     Mehran
    0.72
    ottesville
    0.68
    antage
    0.64
    iel
    0.62
    water
    0.62
    rent
    0.59
     marqu
    0.59
     guiActiveUnfocused
    0.59
    angelo
    0.58
     bearer
    0.58
    Activations Density 0.136%

    No Known Activations