© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 8301
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location or city name, particularly "Guwahati"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stood
    -0.74
     Icar
    -0.73
    where
    -0.71
    shows
    -0.67
     Faster
    -0.65
    bearing
    -0.65
    spin
    -0.64
     Dust
    -0.64
     Patient
    -0.63
     margins
    -0.63
    POSITIVE LOGITS
    ati
    1.08
    oga
    1.02
    apolis
    1.02
    uga
    0.98
    ibo
    0.96
    udi
    0.95
    ya
    0.94
    hedral
    0.94
    eta
    0.92
    ual
    0.92
    Activations Density 0.012%

    No Known Activations