© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 17079
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific technical terms or actions, such as database-related terms, technical specifications, software tools, and physical phenomena like gamma-ray bursts

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and proper nouns related to specific subjects or industries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ£
    -0.79
    minecraft
    -0.74
    jet
    -0.71
    ¯¯¯¯¯¯¯¯
    -0.70
    odox
    -0.70
    Merit
    -0.68
    halla
    -0.67
    URA
    -0.67
    BIT
    -0.67
    ãĥ¥
    -0.67
    POSITIVE LOGITS
    eers
    0.84
     equivalents
    0.65
     itself
    0.62
    âĦ¢:
    0.61
     rul
    0.60
     elders
    0.58
    ishops
    0.56
     intrins
    0.56
     starters
    0.55
     Advocate
    0.54
    Activations Density 0.824%

    No Known Activations