© 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. 9-RES-JB
    11. 4325
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Car" with varying suffixes

    oai_token-act-pair · gpt-3.5-turbo
    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
     wid
    -0.70
     orphans
    -0.69
    etsk
    -0.66
     agric
    -0.66
    artifacts
    -0.61
     advis
    -0.61
    krit
    -0.59
     hikers
    -0.58
     tremend
    -0.57
     situ
    -0.57
    POSITIVE LOGITS
    vale
    0.81
     Seat
    0.80
     Ferry
    0.79
    onne
    0.78
    reau
    0.76
    ucci
    0.74
    ades
    0.73
    ardo
    0.71
    emale
    0.71
    steen
    0.70
    Activations Density 0.174%

    No Known Activations