© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20913
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly locations such as cities in news articles

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically opening parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expire
    -0.69
     treats
    -0.64
     discrim
    -0.64
     hops
    -0.64
     registry
    -0.63
     elect
    -0.62
     macros
    -0.62
     majesty
    -0.62
     multiplication
    -0.61
     retard
    -0.61
    POSITIVE LOGITS
    Reuters
    1.25
    Thom
    1.08
    CBS
    0.98
    AFP
    0.96
    CNN
    0.95
    emphasis
    0.93
    via
    0.92
    credit
    0.92
    formerly
    0.91
    CN
    0.87
    Activations Density 0.045%

    No Known Activations