© 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. 4805
    Prev
    Next
    INDEX
    Explanations

    references to the name "ino" at various activations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "ino" 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
     banner
    -0.70
     scroll
    -0.66
     thumbnail
    -0.65
     vap
    -0.65
     fill
    -0.64
     bore
    -0.62
     Scroll
    -0.62
     clut
    -0.61
     Household
    -0.60
     gull
    -0.60
    POSITIVE LOGITS
    ino
    4.36
    inos
    2.89
    INO
    2.71
    ini
    1.81
    ina
    1.65
    inas
    1.62
    inian
    1.55
    inelli
    1.42
    INA
    1.35
    ano
    1.35
    Activations Density 0.014%

    No Known Activations