© 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. 10-RES-JB
    11. 14042
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or entities, particularly related to Australia

    oai_token-act-pair · gpt-3.5-turbo

    references to Australia and its institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.71
     holiest
    -0.68
    ppings
    -0.66
    Lens
    -0.64
    Ohio
    -0.62
     Cleveland
    -0.62
     Kasich
    -0.61
    lasses
    -0.61
    osen
    -0.61
    bage
    -0.61
    POSITIVE LOGITS
     Aboriginal
    0.96
     Turnbull
    0.89
     Broadcasting
    0.87
    Australia
    0.86
     Defence
    0.85
     Australia
    0.81
     Australians
    0.81
    IRO
    0.80
     Rugby
    0.80
     aboriginal
    0.79
    Activations Density 0.044%

    No Known Activations