Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10846
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name "Ts"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Ts" and its variations, likely indicating a focus on a specific topic or subject related to Tsunamis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mileage
    -0.87
    eering
    -0.68
     turf
    -0.64
     Yankee
    -0.62
    tenance
    -0.61
    esis
    -0.59
     NAS
    -0.58
     Hitchcock
    -0.58
     Western
    -0.58
     Crusader
    -0.58
    POSITIVE LOGITS
    avorite
    1.61
    arnaev
    1.56
    ushima
    1.27
    ugi
    1.17
    izoph
    1.13
    utsu
    1.12
    onga
    1.09
    cham
    1.07
    uda
    1.01
    terness
    1.00
    Activations Density 0.030%

    No Known Activations