© 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. 8-RES-JB
    11. 2671
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns that refer to political entities or figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.70
    interstitial
    -0.68
    ãĥ¬
    -0.65
    tnc
    -0.62
    7601
    -0.62
     ..."
    -0.61
    groupon
    -0.61
    ο
    -0.58
    Els
    -0.58
    Eva
    -0.57
    POSITIVE LOGITS
     meanwhile
    1.45
     reacted
    1.14
     responded
    1.11
     however
    1.10
     also
    1.08
     countered
    1.04
     reportedly
    1.04
     therefore
    1.03
     certainly
    1.01
     understandably
    0.99
    Activations Density 0.658%

    No Known Activations