© 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. 0-RES-JB
    6. 15647
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to names of people or places

    oai_token-act-pair · gpt-3.5-turbo

    the term "inos" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     window
    -0.71
     toler
    -0.68
     bucket
    -0.65
     profile
    -0.63
     Outlook
    -0.62
     CTRL
    -0.61
     aug
    -0.61
     clearance
    -0.61
     saint
    -0.60
     cr
    -0.60
    POSITIVE LOGITS
    inos
    4.60
    ino
    2.46
    inas
    1.78
    INO
    1.68
    inis
    1.33
    inian
    1.33
    anos
    1.30
    inia
    1.24
    ines
    1.23
    obos
    1.19
    Activations Density 0.009%

    No Known Activations