© 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. 11-RES-JB
    6. 1385
    Prev
    Next
    INDEX
    Explanations

    phrases containing the name "Oliver."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Oliver."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    essor
    -0.82
    mble
    -0.79
    ering
    -0.72
    llan
    -0.70
     compensation
    -0.70
    erald
    -0.68
    ilian
    -0.65
    ered
    -0.64
    Downloadha
    -0.62
     deport
    -0.62
    POSITIVE LOGITS
     Twist
    1.04
     Crom
    0.90
     Wend
    0.80
    sen
    0.78
    tein
    0.78
     Kahn
    0.73
    mbuds
    0.73
    sson
    0.71
    atoes
    0.71
    icity
    0.70
    Activations Density 0.054%

    No Known Activations