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

    Neuronpedia

    Jacobian LensNEW
    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. 23732
    Prev
    Next
    INDEX
    Explanations

    movie titles with unusual or unconventional characters or symbols

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the character 'âĢ' followed by 'Ŀ'

    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
     incent
    -0.73
     helpless
    -0.72
     ponder
    -0.70
     ende
    -0.70
     orgasm
    -0.69
     sacrific
    -0.67
     unconscious
    -0.67
     reflection
    -0.67
     answ
    -0.66
     manageable
    -0.66
    POSITIVE LOGITS
    ¯
    0.95
    ï¸
    0.82
    Tea
    0.81
    é¾į
    0.79
    xxx
    0.79
    ef
    0.76
    times
    0.76
    abad
    0.74
    ï¸ı
    0.74
    ttp
    0.74
    Activations Density 0.207%

    No Known Activations