© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4850
    Prev
    Next
    INDEX
    Explanations

    locations, specifically focusing on the state of Queensland

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the regions Queensland and Tasmania

    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
    abet
    -0.81
    fare
    -0.81
    udder
    -0.77
    ãĤ·ãĥ£
    -0.76
    herer
    -0.76
    ronic
    -0.75
    icago
    -0.73
    ocratic
    -0.72
    tered
    -0.71
    ischer
    -0.71
    POSITIVE LOGITS
    ers
    0.90
     Queensland
    0.80
    shire
    0.78
     Gazette
    0.78
     Nickel
    0.73
     Nurs
    0.73
     Rural
    0.72
     Roads
    0.71
     Governments
    0.70
     Springs
    0.70
    Activations Density 0.007%

    No Known Activations