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. 6-RES-JB
    6. 21200
    Prev
    Next
    INDEX
    Explanations

    references to measurements of land or property

    oai_token-act-pair · gpt-3.5-turbo

    measurements related to land size and area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worn
    -0.69
    codes
    -0.67
    actionDate
    -0.63
    ties
    -0.62
    learn
    -0.62
     Reborn
    -0.62
    lishes
    -0.62
    icians
    -0.61
    cross
    -0.60
    ads
    -0.60
    POSITIVE LOGITS
     gorilla
    0.95
     combo
    0.80
     bunker
    0.79
     erection
    0.74
     stare
    0.71
    essee
    0.71
     swath
    0.71
     ult
    0.71
     sized
    0.68
    imeter
    0.67
    Activations Density 0.070%

    No Known Activations