© 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. 8-RES-JB
    11. 2626
    Prev
    Next
    INDEX
    Explanations

    references to the Armenian culture and history

    oai_token-act-pair · gpt-3.5-turbo

    references to Armenia and Armenian identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ered
    -1.05
    erton
    -0.92
    )=(
    -0.90
    utable
    -0.86
    arded
    -0.83
    ers
    -0.82
    ularity
    -0.81
    raltar
    -0.80
    ership
    -0.79
    erd
    -0.76
    POSITIVE LOGITS
     Genocide
    0.82
     Apost
    0.77
    Ô
    0.74
    SHIP
    0.72
     Airlines
    0.68
     PRESS
    0.67
    BIL
    0.66
     shake
    0.64
     tilt
    0.64
    nex
    0.64
    Activations Density 0.079%

    No Known Activations