© 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. 6-RES-JB
    11. 13806
    Prev
    Next
    INDEX
    Explanations

    text related to verification and systems

    oai_token-act-pair · gpt-3.5-turbo

    references to systems, tools, or platforms that facilitate some form of organization or functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -1.14
    ãĥĥãĥī
    -0.94
    ãģĦ
    -0.93
    ãĥ©ãĥ³
    -0.89
    é¾įå
    -0.81
    ãĤ¨ãĥ«
    -0.78
    çĶ°
    -0.76
    bernatorial
    -0.75
    èª
    -0.75
    æ©
    -0.75
    POSITIVE LOGITS
     extraord
    0.77
    orously
    0.68
     geared
    0.67
     whereby
    0.65
     Compass
    0.64
    matically
    0.64
     coupled
    0.64
     nationwide
    0.63
     Pinterest
    0.63
     Euph
    0.62
    Activations Density 0.412%

    No Known Activations