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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 19257
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations, particularly the city of Damascus

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographic locations, particularly cities in Syria

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    owler
    -0.89
    opsy
    -0.80
    unal
    -0.80
    ographics
    -0.78
    ographically
    -0.77
    INAL
    -0.75
    rity
    -0.75
    lying
    -0.75
    inarily
    -0.74
    ridges
    -0.74
    POSITIVE LOGITS
    ascus
    1.12
     Damascus
    0.96
    ites
    0.81
     suburbs
    0.78
    atos
    0.74
    sels
    0.73
    ien
    0.73
    soever
    0.73
     suburb
    0.71
     Assad
    0.71
    Activations Density 0.009%

    No Known Activations