© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 9208
    Prev
    Next
    INDEX
    Explanations

    words related to the name "Beaufort"

    oai_token-act-pair · gpt-3.5-turbo

    references to the geographic locations or names associated with Beaufort and Plymouth

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

    No Comments

    Negative Logits
    acea
    -0.87
    atin
    -0.83
    alez
    -0.83
    ograp
    -0.79
    nih
    -0.79
    iary
    -0.79
    oulos
    -0.78
    aid
    -0.78
    leaders
    -0.78
    iques
    -0.76
    POSITIVE LOGITS
    ignty
    0.93
     Musk
    0.83
    llan
    0.81
     Locke
    0.77
     Cook
    0.77
     Bent
    0.76
    ño
    0.74
    ilk
    0.73
     Swan
    0.72
     Borders
    0.72
    Activations Density 0.025%

    No Known Activations