© 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. 18657
    Prev
    Next
    INDEX
    Explanations

    locations or objects named after places

    oai_token-act-pair · gpt-3.5-turbo

    specific types of food establishments and related locations

    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
     Incarn
    -0.80
     qualitative
    -0.77
     fingerprints
    -0.74
     Izan
    -0.74
    REDACTED
    -0.68
     symmetry
    -0.68
     acron
    -0.68
     adject
    -0.67
     canonical
    -0.67
     prophe
    -0.66
    POSITIVE LOGITS
    pee
    1.19
    wagon
    1.19
    rolley
    1.03
    pees
    1.00
     wagon
    1.00
    inery
    1.00
    ooters
    0.98
    eway
    0.97
    club
    0.94
     enclosure
    0.93
    Activations Density 0.531%

    No Known Activations