© 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. 10725
    Prev
    Next
    INDEX
    Explanations

    political and governmental terms

    oai_token-act-pair · gpt-3.5-turbo

    a specific character or symbol used in various contexts

    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
     Palestin
    -0.74
     sacrific
    -0.72
     incorpor
    -0.72
     ende
    -0.72
     notor
    -0.70
     seiz
    -0.70
     strugg
    -0.69
    cember
    -0.66
     agre
    -0.65
     scattering
    -0.65
    POSITIVE LOGITS
    ¯
    1.19
    ï¸ı
    0.90
    #$
    0.82
    ef
    0.81
    tab
    0.79
    âĢł
    0.79
    Tea
    0.79
    times
    0.75
    xxx
    0.74
    sic
    0.73
    Activations Density 0.190%

    No Known Activations