© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 24024
    Prev
    Next
    INDEX
    Explanations

    mentions of various aspects related to a house, such as its presence, types, conditions, and locations

    oai_token-act-pair · gpt-3.5-turbo

    multiple mentions of the word "house."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneously
    -0.80
    uyomi
    -0.72
    psey
    -0.70
    ICAL
    -0.69
    aneous
    -0.69
     guiActiveUn
    -0.68
    iferation
    -0.67
    DragonMagazine
    -0.66
    NetMessage
    -0.65
    istical
    -0.63
    POSITIVE LOGITS
    wife
    1.46
    wives
    1.43
    keeping
    1.25
    keeper
    1.13
    mates
    1.09
    warming
    1.08
    boat
    1.07
    boats
    1.04
    plant
    1.03
    mate
    0.98
    Activations Density 0.029%

    No Known Activations