© 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. 1-RES-JB
    11. 13451
    Prev
    Next
    INDEX
    Explanations

    Keiv, a city in Ukraine

    oai_token-act-pair · gpt-3.5-turbo

    names and mentions of specific places and people, particularly related to Kiev

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     recurring
    -0.66
    holders
    -0.62
    ombs
    -0.61
     ports
    -0.59
     Binary
    -0.58
     racks
    -0.58
    ŃĶ
    -0.58
     Adamant
    -0.57
     drinking
    -0.56
    cross
    -0.55
    POSITIVE LOGITS
    iev
    1.62
    icz
    1.33
    rov
    1.13
    rolet
    0.93
    ideo
    0.91
    æĪ¦
    0.90
    ovsky
    0.88
    chenko
    0.85
    axies
    0.85
    о
    0.83
    Activations Density 0.008%

    No Known Activations