© 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. 11-RES-JB
    11. 7
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical or geological elements such as architecture, fossils, sound engineering, and ancient materials

    oai_token-act-pair · gpt-3.5-turbo

    references to notable historical entities or landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çī
    -0.73
     Bullets
    -0.70
    ãĤ¡
    -0.68
    ãĤĬ
    -0.67
     Tackle
    -0.66
     unfocusedRange
    -0.61
     Shutdown
    -0.60
    deals
    -0.60
    ggles
    -0.60
     Fixes
    -0.60
    POSITIVE LOGITS
     extant
    1.31
     studied
    1.15
     ever
    1.12
     anywhere
    1.12
     existed
    1.10
     documented
    1.08
     recorded
    1.07
     exist
    1.05
     preserved
    1.05
     discovered
    1.03
    Activations Density 0.293%

    No Known Activations