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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 1341
    Prev
    Next
    INDEX
    Explanations

    references to the care or ownership of pets

    oai_token-act-pair · gpt-3.5-turbo

    references to pets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usra
    -0.82
    Arab
    -0.72
     Arab
    -0.72
     glac
    -0.70
    Å
    -0.68
     fir
    -0.68
     Johann
    -0.66
     centrif
    -0.66
     ellipt
    -0.66
    oton
    -0.65
    POSITIVE LOGITS
     pets
    3.23
     Pets
    2.43
     renters
    1.04
     mounts
    1.00
     summons
    0.98
     refunds
    0.93
     rodents
    0.93
     pests
    0.91
     macros
    0.89
     roomm
    0.88
    Activations Density 0.022%

    No Known Activations