© 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. 8-RES-JB
    11. 2732
    Prev
    Next
    INDEX
    Explanations

    mentions of locations or entities related to British regions or institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "British" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.95
    ographed
    -0.79
    ovie
    -0.78
    inarily
    -0.78
    ologies
    -0.77
    regation
    -0.77
    eger
    -0.76
    neapolis
    -0.74
    pty
    -0.74
    uably
    -0.73
    POSITIVE LOGITS
     Isles
    1.41
     Columbia
    1.39
     Columb
    1.34
     Airways
    1.25
     Virgin
    1.01
     Parliament
    0.94
     Overse
    0.92
     Union
    0.90
     Broadcasting
    0.88
     Antarctic
    0.88
    Activations Density 0.028%

    No Known Activations