© 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. 1-RES-JB
    11. 20315
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ondo."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mondo" and terms related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TY
    -0.86
    ttle
    -0.84
    TPS
    -0.73
    ty
    -0.71
    natureconservancy
    -0.70
    txt
    -0.67
    mat
    -0.67
    alions
    -0.66
    children
    -0.64
    tty
    -0.63
    POSITIVE LOGITS
    ondo
    1.15
    ãĥ¼ãĥĨãĤ£
    0.72
    qua
    0.71
    oga
    0.69
    ãĥ¼ãĥĨ
    0.67
     Alley
    0.66
    etheless
    0.66
    iffe
    0.65
    oso
    0.64
    olin
    0.64
    Activations Density 0.004%

    No Known Activations