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. 23908
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical movement or spatial distribution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating widespread distribution or presence across various places

    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
    iliate
    -0.78
    ignt
    -0.72
     Rasmussen
    -0.69
    interstitial
    -0.69
    uca
    -0.68
    TION
    -0.66
    EStream
    -0.66
    ————
    -0.66
    thood
    -0.65
    govtrack
    -0.65
    POSITIVE LOGITS
     room
    1.35
     floor
    1.19
     halls
    1.19
     floors
    1.19
     rooft
    1.19
     globe
    1.17
     shelves
    1.13
     streets
    1.12
     place
    1.11
     entire
    1.08
    Activations Density 0.171%

    No Known Activations