© 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. 10-RES-JB
    11. 10597
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    references to collective actions or observations involving groups of people

    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
     Rebellion
    -0.70
    Offline
    -0.63
     Millennium
    -0.59
     Recession
    -0.59
     Toggle
    -0.59
    INGTON
    -0.58
    âĦ¢:
    -0.57
    Govern
    -0.56
    CLASSIFIED
    -0.56
     Enh
    -0.55
    POSITIVE LOGITS
     then
    1.35
     also
    1.24
     proceeded
    1.08
     eventually
    1.07
     subsequently
    1.06
     wore
    1.04
     hoped
    1.00
     waited
    0.99
     drew
    0.98
     THEN
    0.98
    Activations Density 0.287%

    No Known Activations