© 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. 6-RES-JB
    11. 7488
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to recognition

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "Hon" in reference to honors or honors-related achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Apocalypse
    -0.73
    phrine
    -0.73
     Barbarian
    -0.71
     Clicker
    -0.70
     Panther
    -0.66
     Panic
    -0.65
     Spray
    -0.63
     Fired
    -0.63
     Warfare
    -0.62
     hypert
    -0.62
    POSITIVE LOGITS
    orable
    1.40
    olulu
    1.40
    esty
    1.20
    eous
    1.16
    ouri
    0.97
    oring
    0.95
    iton
    0.92
    ored
    0.91
    ilo
    0.90
    Hon
    0.90
    Activations Density 0.013%

    No Known Activations