© 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. 11-RES-JB
    11. 2696
    Prev
    Next
    INDEX
    Explanations

    terms related to proper nouns, specifically names or references to individuals, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    specific names or identifiers of people and organizations

    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
     Fors
    -0.99
     Gors
    -0.96
     rall
    -0.83
     RIS
    -0.78
     Rak
    -0.77
     Gork
    -0.77
     Frozen
    -0.76
     Slov
    -0.75
     Ruff
    -0.74
     Ernst
    -0.74
    POSITIVE LOGITS
    am
    2.02
    AM
    1.79
    ams
    1.76
    amia
    1.61
    ammy
    1.58
    amy
    1.57
    amm
    1.47
    amic
    1.46
    aml
    1.45
    ami
    1.45
    Activations Density 0.096%

    No Known Activations