© 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. 11318
    Prev
    Next
    INDEX
    Explanations

    mentions of international borders and specific publications like "The Economist" magazine

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations and geographic locations

    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
    esan
    -0.79
    iste
    -0.77
    sters
    -0.72
    osaurus
    -0.72
    estern
    -0.71
     predator
    -0.68
    wan
    -0.66
    dinand
    -0.66
    alore
    -0.64
    ographical
    -0.63
    POSITIVE LOGITS
    nces
    0.88
     Borders
    0.82
    ¶ħ
    0.78
    dry
    0.77
    soever
    0.77
    ignty
    0.75
     Writing
    0.72
     Thomson
    0.72
    Write
    0.72
    words
    0.71
    Activations Density 0.034%

    No Known Activations