© 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. 9-RES-JB
    6. 3328
    Prev
    Next
    INDEX
    Explanations

    phrases related to car brands and models

    oai_token-act-pair · gpt-3.5-turbo

    instances of the brand name "Honda."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kers
    -0.92
    ablishment
    -0.86
    nels
    -0.79
    acular
    -0.78
    lopp
    -0.78
    dict
    -0.76
    itions
    -0.76
    kies
    -0.74
    zees
    -0.74
    ebus
    -0.72
    POSITIVE LOGITS
     Karin
    0.86
     Accord
    0.85
     Civic
    0.84
     Oro
    0.84
     Rouse
    0.83
     Prelude
    0.75
     Malf
    0.74
     Fit
    0.74
     Rica
    0.70
    asaki
    0.68
    Activations Density 0.094%

    No Known Activations