© 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. 2654
    Prev
    Next
    INDEX
    Explanations

    locations such as cities or countries

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" along with associated location phrases

    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
     certs
    -0.87
    Chuck
    -0.85
    wolves
    -0.78
    NFL
    -0.77
    UGH
    -0.76
    keyes
    -0.73
    Kids
    -0.72
    Feed
    -0.70
    Skip
    -0.68
    STEM
    -0.68
    POSITIVE LOGITS
     Istanbul
    1.80
     Kuala
    1.69
     Ankara
    1.66
     Budapest
    1.65
     Tehran
    1.63
     Vienna
    1.59
     Cairo
    1.57
     Jakarta
    1.57
     Madrid
    1.57
     Bangkok
    1.56
    Activations Density 0.268%

    No Known Activations