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. 9-RES-JB
    6. 729
    Prev
    Next
    INDEX
    Explanations

    specific locations described by streets and avenues

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to locations and intersections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.78
    >[
    -0.75
    ubi
    -0.73
    oglobin
    -0.72
     nom
    -0.72
    lied
    -0.72
     virt
    -0.71
    ndra
    -0.70
    istically
    -0.69
     indisp
    -0.68
    POSITIVE LOGITS
     Boulevard
    1.27
     Broadway
    1.18
     Avenue
    1.17
     Interstate
    1.12
     Sunset
    1.12
     Highway
    1.11
     Canal
    1.09
     Elm
    1.08
     Riverside
    1.07
     Route
    1.06
    Activations Density 0.074%

    No Known Activations