© 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. 1-RES-JB
    11. 3403
    Prev
    Next
    INDEX
    Explanations

    references to the sports team "Blues."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific sports team, "Blues"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igators
    -0.74
    ILY
    -0.73
    lying
    -0.71
    Population
    -0.69
    iannopoulos
    -0.68
     WATCHED
    -0.67
    Political
    -0.66
    igated
    -0.66
     PAX
    -0.64
    icles
    -0.64
    POSITIVE LOGITS
    hift
    1.27
     Blues
    1.26
    creen
    0.93
     blues
    0.90
    hirt
    0.87
    berries
    0.81
    ignt
    0.74
    pace
    0.72
    hess
    0.71
    uits
    0.71
    Activations Density 0.005%

    No Known Activations