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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 5941
    Prev
    Next
    INDEX
    Explanations

    mentions or references to community-related events or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to community colleges and related schemes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atan
    -0.91
     athlet
    -0.75
    ottenham
    -0.66
     indo
    -0.63
    packing
    -0.61
    iosyncr
    -0.61
     Wasserman
    -0.60
    hani
    -0.60
    esty
    -0.60
     Difference
    -0.60
    POSITIVE LOGITS
    USS
    0.87
    SEE
    0.79
    chest
    0.70
    verse
    0.66
    apo
    0.63
    VII
    0.61
    vasive
    0.61
    ãĤ¢ãĥ«
    0.60
    reci
    0.60
    adden
    0.59
    Activations Density 0.000%

    No Known Activations