© 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. 20740
    Prev
    Next
    INDEX
    Explanations

    names of people or places with the substring "atsu"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and brands related to Japanese culture or products

    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
    fulness
    -0.86
    cloth
    -0.84
    leaf
    -0.71
    crow
    -0.71
    runner
    -0.70
    fect
    -0.69
    castle
    -0.68
    bow
    -0.68
    ability
    -0.66
    formation
    -0.65
    POSITIVE LOGITS
    uyomi
    0.93
    xual
    0.92
    ermott
    0.81
    ãĤ´ãĥ³
    0.80
    yip
    0.79
    utra
    0.77
    urst
    0.76
    æ©Ł
    0.74
    ļéĨĴ
    0.73
    ãĥĥãĥī
    0.72
    Activations Density 0.041%

    No Known Activations