© 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. 4-RES-JB
    11. 10080
    Prev
    Next
    INDEX
    Explanations

    words related to places or locations, particularly those ending in "awa"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "awa" or related terms indicating a specific location or relevant context

    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
    оÐ
    -0.70
    ologically
    -0.67
    onym
    -0.67
    urgy
    -0.65
    tone
    -0.65
     Eliot
    -0.65
    book
    -0.64
    hetical
    -0.62
     sheet
    -0.61
    sheet
    -0.60
    POSITIVE LOGITS
    aii
    1.16
    awa
    1.02
     Shogun
    0.86
    iba
    0.85
    oka
    0.82
    ichi
    0.79
    velength
    0.79
    ÅŁ
    0.78
    orthy
    0.78
    arij
    0.77
    Activations Density 0.010%

    No Known Activations