© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    references to lanes, especially in the context of transportation or paths

    oai_token-act-pair · gpt-3.5-turbo

    references to lanes in traffic or road contexts

    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
    anamo
    -0.78
    sonian
    -0.73
     Seym
    -0.73
    etheus
    -0.73
    icism
    -0.72
    krit
    -0.70
    PLIC
    -0.70
    pson
    -0.69
    orical
    -0.68
    Birth
    -0.68
    POSITIVE LOGITS
    lane
    0.88
     closures
    0.84
     lane
    0.77
     divid
    0.77
     congestion
    0.74
    keeper
    0.71
    ©¶æ
    0.71
    wagon
    0.71
    keepers
    0.68
     swaps
    0.67
    Activations Density 0.045%

    No Known Activations