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. 8-RES-JB
    6. 14699
    Prev
    Next
    INDEX
    Explanations

    mentions of weights or measurements in pounds

    oai_token-act-pair · gpt-3.5-turbo

    references to weight and measurements in pounds and kilograms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.80
    cknow
    -0.78
    opol
    -0.77
    choes
    -0.73
    vironment
    -0.73
     externalToEVAOnly
    -0.71
     Nare
    -0.70
    inav
    -0.69
     Emin
    -0.67
    ovie
    -0.66
    POSITIVE LOGITS
     sterling
    1.23
    cake
    1.00
     gorilla
    0.98
     pounds
    0.97
    lbs
    0.96
     heavier
    0.93
     lbs
    0.93
     overweight
    0.89
     weight
    0.87
    cakes
    0.84
    Activations Density 0.027%

    No Known Activations