© 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. 9-RES-JB
    11. 17994
    Prev
    Next
    INDEX
    Explanations

    historical figures and their relations to others

    oai_token-act-pair · gpt-3.5-turbo

    references to historical royalty and their lineage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FOX
    -0.99
    VIDEO
    -0.90
    ratom
    -0.90
     clips
    -0.87
     VIDEO
    -0.85
     salsa
    -0.83
     clip
    -0.83
     pickup
    -0.82
     pickups
    -0.82
    ooters
    -0.82
    POSITIVE LOGITS
     Empress
    1.40
     Emperor
    1.32
     emperor
    1.28
     Constantinople
    1.26
     throne
    1.26
     royal
    1.21
     heir
    1.17
     Augustus
    1.16
     Carth
    1.14
     kingdoms
    1.14
    Activations Density 0.617%

    No Known Activations