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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 19295
    Prev
    Next
    INDEX
    Explanations

    words related to legal entities with "Sw" in them

    oai_token-act-pair · gpt-3.5-turbo

    the name "Swami" or variants of it in various contexts

    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
    EStream
    -0.72
    cised
    -0.68
    BILITY
    -0.67
     sidx
    -0.66
    OPLE
    -0.65
     Pigs
    -0.64
    代
    -0.63
     burying
    -0.63
    66666666
    -0.63
     theater
    -0.61
    POSITIVE LOGITS
    inton
    1.10
     Sw
    1.03
    allows
    1.01
    artz
    1.01
    indle
    1.01
    Sw
    0.98
    imming
    0.98
    addle
    0.98
    immer
    0.95
    ifty
    0.94
    Activations Density 0.004%

    No Known Activations