© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20664
    Prev
    Next
    INDEX
    Explanations

    words related to specific organizations or groups

    oai_token-act-pair · gpt-3.5-turbo

    specific letter sequences or patterns that might indicate certain names or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kat
    -0.88
    itte
    -0.83
    Beck
    -0.80
     Johnston
    -0.79
     jew
    -0.76
     Tinker
    -0.76
     McD
    -0.74
     Lennon
    -0.73
     iT
    -0.73
     Jordan
    -0.72
    POSITIVE LOGITS
    UR
    1.26
    ur
    1.22
    ure
    1.16
    ural
    1.14
    mur
    1.11
    urs
    1.11
    ür
    1.07
    Mur
    1.07
    uri
    1.02
    uria
    1.02
    Activations Density 0.346%

    No Known Activations