© 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. 10-RES-JB
    11. 20507
    Prev
    Next
    INDEX
    Explanations

    passages related to the formation or creation of objects or substances

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of processes and formations of organic or manufactured entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Dispatch
    -0.75
     Nationwide
    -0.71
    ilitation
    -0.70
    Politics
    -0.70
     Compliance
    -0.69
     Accountability
    -0.68
    Gov
    -0.68
    Ops
    -0.67
    Govern
    -0.67
    review
    -0.67
    POSITIVE LOGITS
     beads
    1.25
     crystals
    1.25
     particles
    1.18
     fragments
    1.12
     feathers
    1.11
     metals
    1.05
     metallic
    1.05
     adhesive
    1.05
     insects
    1.05
     decorative
    1.04
    Activations Density 0.719%

    No Known Activations