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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3608
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or communities, particularly focusing on "Village"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Village" in various contexts

    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
    cies
    -0.99
    odynam
    -0.87
    henko
    -0.83
    iscopal
    -0.83
    etr
    -0.83
    manship
    -0.82
    etric
    -0.81
    cific
    -0.81
    ional
    -0.79
    irection
    -0.79
    POSITIVE LOGITS
     Village
    1.17
     Halls
    0.89
     Plaza
    0.87
     Taxi
    0.84
     Clinic
    0.83
     Voice
    0.82
     District
    0.82
     Weekend
    0.82
     Cemetery
    0.82
     Paper
    0.80
    Activations Density 0.013%

    No Known Activations