© 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. 8-RES-JB
    11. 10819
    Prev
    Next
    INDEX
    Explanations

    locations or addresses, particularly in the United States

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and their corresponding states or regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.87
    henko
    -0.72
    andowski
    -0.70
    ufact
    -0.68
    mania
    -0.66
    Proof
    -0.66
    Afee
    -0.65
    toggle
    -0.64
    ãĤ¨ãĥ«
    -0.64
    loads
    -0.63
    POSITIVE LOGITS
    ./
    0.69
     Supervisor
    0.68
     Dept
    0.65
    achusetts
    0.64
     tradem
    0.64
    ARA
    0.61
    ithing
    0.61
    ometown
    0.60
     subur
    0.60
     STATE
    0.59
    Activations Density 0.036%

    No Known Activations