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. 21879
    Prev
    Next
    INDEX
    Explanations

    locations in Washington, D.C

    oai_token-act-pair · gpt-3.5-turbo

    the city name and its abbreviation for Washington, D.C

    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
     chopping
    -0.71
     sidel
    -0.71
     mant
    -0.71
     acron
    -0.71
     retrospective
    -0.61
     liquid
    -0.60
     increasing
    -0.60
     rule
    -0.59
     frameworks
    -0.58
     roundup
    -0.58
    POSITIVE LOGITS
    Va
    1.06
    town
    0.77
    sylvania
    0.74
    essee
    0.71
    rex
    0.70
    lux
    0.70
    apolis
    0.69
    edu
    0.68
    western
    0.68
    C
    0.68
    Activations Density 0.036%

    No Known Activations