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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6872
    Prev
    Next
    INDEX
    Explanations

    tokens related to religious or political entities specifically involving Hinduism and the Rashtriya Swayamsevak Sangh (RSS)

    oai_token-act-pair · gpt-3.5-turbo

    elements related to specific organizations or groups

    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
    hetically
    -0.64
    userc
    -0.64
    lehem
    -0.61
    TAIN
    -0.60
     livest
    -0.60
    ãĥ´
    -0.59
     citiz
    -0.59
     skim
    -0.59
    nown
    -0.58
     ripe
    -0.57
    POSITIVE LOGITS
    backer
    0.81
    orce
    0.63
     CTR
    0.60
    oxide
    0.59
    vous
    0.59
     cuff
    0.57
     Mond
    0.57
    zik
    0.57
    othal
    0.55
     Zot
    0.55
    Activations Density 1.010%

    No Known Activations