© 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. 11-RES-JB
    11. 7771
    Prev
    Next
    INDEX
    Explanations

    references to a specific place or position inside a vehicle

    oai_token-act-pair · gpt-3.5-turbo

    references to passengers in various contexts

    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
    arios
    -0.75
    ologies
    -0.72
     Marble
    -0.72
    sts
    -0.69
    ét
    -0.68
    achu
    -0.68
     foreclosure
    -0.66
    ritz
    -0.64
    Ĵ
    -0.63
    mberg
    -0.63
    POSITIVE LOGITS
     pigeon
    1.05
     onboard
    1.02
     compartment
    1.02
     ferry
    0.96
     cabin
    0.95
     passenger
    0.95
     airliner
    0.94
     passengers
    0.94
     pige
    0.94
     airlines
    0.93
    Activations Density 0.042%

    No Known Activations