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. 11-RES-JB
    6. 23409
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations in Eastern Europe

    oai_token-act-pair · gpt-3.5-turbo

    references to Eastern Europe

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.75
    among
    -0.71
    UTH
    -0.70
    BALL
    -0.70
    aceous
    -0.69
    balls
    -0.68
    pload
    -0.67
    ificial
    -0.65
    aday
    -0.65
    pell
    -0.65
    POSITIVE LOGITS
     Partnership
    0.87
     Shore
    0.87
     Mediterranean
    0.85
     bloc
    0.83
     European
    0.78
     Kentucky
    0.77
     Orthodox
    0.76
     Congo
    0.76
     Conference
    0.75
     blot
    0.75
    Activations Density 0.017%

    No Known Activations