© 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. 1773
    Prev
    Next
    INDEX
    Explanations

    Russian Cyrillic characters, possibly related to the word "power."

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or sequence of characters in the text

    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
    ãĤ£
    -0.90
    ãĤ©
    -0.88
    Ö¼
    -0.86
    tones
    -0.85
    ultan
    -0.77
    ESSION
    -0.76
    urrent
    -0.76
    gian
    -0.74
    theless
    -0.74
     IPM
    -0.74
    POSITIVE LOGITS
    âĹ¼
    0.70
     favour
    0.68
     Leviathan
    0.64
    imura
    0.62
    zzi
    0.61
    Stra
    0.60
    ppy
    0.59
    erers
    0.59
    patrick
    0.59
    warm
    0.59
    Activations Density 0.092%

    No Known Activations