© 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. 2-RES-JB
    11. 24109
    Prev
    Next
    INDEX
    Explanations

    elements of a particular language or characters that are part of a specific written system

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols, particularly those that indicate strong emphasis or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngth
    -0.87
    meal
    -0.78
     Skydragon
    -0.77
    matically
    -0.76
    manship
    -0.75
    cano
    -0.72
     hitch
    -0.71
    Else
    -0.70
    haps
    -0.69
    pointers
    -0.69
    POSITIVE LOGITS
    ±
    0.95
    į
    0.92
    ãĥ¼
    0.87
    ب
    0.86
    ÙĪ
    0.84
    Ù
    0.83
    ¢
    0.83
    ĭ
    0.82
    س
    0.81
    Ø
    0.81
    Activations Density 0.004%

    No Known Activations