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. 7-RES-JB
    6. 16254
    Prev
    Next
    INDEX
    Explanations

    mentions of specific measurements of space, particularly square feet

    oai_token-act-pair · gpt-3.5-turbo

    measurements of area expressed in square feet or miles

    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
    intent
    -0.69
    alys
    -0.69
     Cron
    -0.62
    etheless
    -0.62
     Noon
    -0.61
    gotten
    -0.61
     Cance
    -0.60
    Lear
    -0.60
    alg
    -0.60
     cyn
    -0.59
    POSITIVE LOGITS
    essions
    0.79
    ifice
    0.77
    ²
    0.76
    artment
    0.73
    .:
    0.72
    ynthesis
    0.72
    housing
    0.70
     enclosed
    0.70
    .;
    0.70
    ouse
    0.69
    Activations Density 0.048%

    No Known Activations