© 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. 8-RES-JB
    11. 3259
    Prev
    Next
    INDEX
    Explanations

    the name "Peterson."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the individual named Peterson

    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
    creen
    -0.92
    sheets
    -0.81
    rooms
    -0.78
    UV
    -0.75
    sheet
    -0.71
    hazard
    -0.70
    utter
    -0.70
     negotiator
    -0.69
    ARDS
    -0.68
    uid
    -0.68
    POSITIVE LOGITS
     Peterson
    0.92
    leased
    0.71
    asus
    0.71
     Ake
    0.71
    ertodd
    0.67
    lund
    0.66
    ansas
    0.65
    VILLE
    0.65
    ËĪ
    0.65
    ERSON
    0.64
    Activations Density 0.087%

    No Known Activations