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. 4-RES-JB
    6. 9798
    Prev
    Next
    INDEX
    Explanations

    locations described by street names and blocks

    oai_token-act-pair · gpt-3.5-turbo

    geographic locations, particularly street names and directions

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

    No Comments

    Negative Logits
    wcsstore
    -0.99
    Äĩ
    -0.86
     hitherto
    -0.80
     analysed
    -0.76
     learnt
    -0.74
     toget
    -0.72
     analyse
    -0.71
    ocrats
    -0.71
    otle
    -0.71
     organise
    -0.71
    POSITIVE LOGITS
     Parkway
    1.07
    lake
    1.07
     Boulevard
    1.06
    west
    1.05
     Blvd
    1.04
     Plaza
    1.03
     Corridor
    1.02
     Broadway
    0.98
    West
    0.94
     Avenue
    0.93
    Activations Density 0.059%

    No Known Activations