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. 10-RES-JB
    6. 19404
    Prev
    Next
    INDEX
    Explanations

    mentions of specific holidays or celebrations

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms related to celebrations or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obin
    -0.87
    selves
    -0.87
    alist
    -0.81
    think
    -0.77
    quickShipAvailable
    -0.77
    VICE
    -0.76
    unda
    -0.75
    Downloadha
    -0.75
    hari
    -0.74
    vati
    -0.74
    POSITIVE LOGITS
     Choice
    1.12
     Landing
    1.08
     Disease
    1.06
     Place
    1.02
     Mansion
    0.98
     Island
    0.97
     Revenge
    0.92
     Miracle
    0.90
     Angels
    0.90
     Picks
    0.89
    Activations Density 0.068%

    No Known Activations