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. 18190
    Prev
    Next
    INDEX
    Explanations

    mentions of names, especially the name "Yas" at various activations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Yas" and "Amit"

    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
    arity
    -0.86
    ichick
    -0.75
    Transfer
    -0.72
     Africans
    -0.69
    ancial
    -0.69
     Lomb
    -0.68
    roads
    -0.67
     African
    -0.67
    gomery
    -0.66
    source
    -0.65
    POSITIVE LOGITS
     Yas
    1.20
     seiz
    0.98
     mosqu
    0.95
    ushi
    0.88
     resil
    0.87
     redes
    0.87
     suspic
    0.83
     simultane
    0.80
    uki
    0.80
    ©¶æ
    0.75
    Activations Density 0.012%

    No Known Activations