Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10660
    Prev
    Next
    INDEX
    Explanations

    locations or addresses in a specific format (ending in " Avenue")

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific street or avenue names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dwar
    -0.70
    =-=-=-=-=-=-=-=-
    -0.68
    ptions
    -0.67
     ref
    -0.67
     flu
    -0.66
     dism
    -0.65
     forg
    -0.65
     weaker
    -0.64
     transparent
    -0.63
     dwarf
    -0.62
    POSITIVE LOGITS
     Avenue
    3.45
     Ave
    2.39
     Boulevard
    2.10
     Street
    1.96
     avenue
    1.63
     Aven
    1.62
     Parkway
    1.49
    Street
    1.49
     Blvd
    1.48
     Drive
    1.41
    Activations Density 0.014%

    No Known Activations