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. 8-RES-JB
    6. 2878
    Prev
    Next
    INDEX
    Explanations

    prominent groups of people in different settings

    oai_token-act-pair · gpt-3.5-turbo

    references to groups or large numbers of individuals

    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
    inventoryQuantity
    -0.84
    senal
    -0.67
     Anyway
    -0.67
     Anything
    -0.65
    ãģĻ
    -0.62
     Narr
    -0.61
    $.
    -0.60
    Honest
    -0.60
    ãĤ¶
    -0.59
     Teacher
    -0.59
    POSITIVE LOGITS
     participated
    1.15
     perished
    1.08
     emerged
    1.06
     were
    1.01
     specialize
    0.99
     have
    0.98
     died
    0.98
     succumbed
    0.98
     sprang
    0.95
     are
    0.95
    Activations Density 0.298%

    No Known Activations