© 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. 10-RES-JB
    11. 20290
    Prev
    Next
    INDEX
    Explanations

    proper nouns or phrases related to significant historical or fictional events

    oai_token-act-pair · gpt-3.5-turbo

    references to significant titles or themes associated with "Final," "Great," and "Old."

    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
     diligence
    -0.75
    ouses
    -0.75
     boards
    -0.73
     tackling
    -0.73
    Downloadha
    -0.73
     expertise
    -0.73
     journalism
    -0.72
    clinton
    -0.72
     radios
    -0.72
    terday
    -0.71
    POSITIVE LOGITS
     Ones
    1.42
     Era
    1.23
     Continent
    1.20
     Shirt
    1.18
     Problem
    1.14
     Relationship
    1.14
     Hours
    1.11
     Age
    1.11
     Principle
    1.11
     Years
    1.10
    Activations Density 0.181%

    No Known Activations