Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 23532
    Prev
    Next
    INDEX
    Explanations

    words related to houses

    oai_token-act-pair · gpt-3.5-turbo

    references to houses, particularly in various contexts or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneously
    -0.72
     guiActiveUn
    -0.71
    DragonMagazine
    -0.70
     CNS
    -0.68
    ICAL
    -0.65
     Nieto
    -0.64
     clipboard
    -0.60
    istical
    -0.60
    aneous
    -0.60
    onal
    -0.60
    POSITIVE LOGITS
    wives
    1.77
    wife
    1.75
    keeping
    1.50
    warming
    1.36
    keeper
    1.33
    keepers
    1.27
    boats
    1.22
    boat
    1.19
    maid
    1.18
    plant
    1.18
    Activations Density 0.059%

    No Known Activations