© 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. 4-RES-JB
    11. 17174
    Prev
    Next
    INDEX
    Explanations

    references to parked vehicles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "parked" and its variations related to vehicles

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

    No Comments

    Negative Logits
     Flavoring
    -1.04
    vernment
    -0.80
    adeon
    -0.79
    ï¸ı
    -0.75
    theless
    -0.71
    é¾įå¥ij士
    -0.70
    conom
    -0.67
    é¾įåĸļ士
    -0.67
    omever
    -0.66
    skin
    -0.63
    POSITIVE LOGITS
     parked
    1.07
    atoon
    0.71
     dere
    0.68
     parking
    0.68
    raint
    0.67
     empty
    0.66
     atop
    0.66
     around
    0.66
     garage
    0.66
     DeL
    0.66
    Activations Density 0.018%

    No Known Activations