© 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. 18409
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity named "Bleeding Cool"

    oai_token-act-pair · gpt-3.5-turbo

    words related to bleeding and injuries

    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
     tert
    -0.75
    ICAN
    -0.75
     pse
    -0.71
     referen
    -0.70
    FML
    -0.69
    »Ĵ
    -0.67
    ADRA
    -0.63
     citiz
    -0.63
    ij士
    -0.62
     bluff
    -0.61
    POSITIVE LOGITS
    osate
    0.76
    ancy
    0.75
    ï¸ı
    0.75
    nir
    0.74
    ifix
    0.67
    ÑĮ
    0.65
     tissues
    0.65
    åŃIJ
    0.62
    idon
    0.61
    mann
    0.60
    Activations Density 0.119%

    No Known Activations