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. 9-RES-JB
    6. 19337
    Prev
    Next
    INDEX
    Explanations

    references to physical buildings, specifically houses

    oai_token-act-pair · gpt-3.5-turbo

    references to houses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUn
    -0.78
    aneously
    -0.70
    ICAL
    -0.70
    NetMessage
    -0.65
     GOODMAN
    -0.64
    uyomi
    -0.64
    DragonMagazine
    -0.64
    gey
    -0.64
    gomery
    -0.63
    istical
    -0.62
    POSITIVE LOGITS
    wife
    1.57
    wives
    1.54
    keeping
    1.29
    warming
    1.26
    mates
    1.20
    keeper
    1.14
    plant
    1.14
    boat
    1.11
    boats
    1.11
    mate
    1.10
    Activations Density 0.039%

    No Known Activations