© 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. 1-RES-JB
    11. 3854
    Prev
    Next
    INDEX
    Explanations

    historical and political terms or names

    oai_token-act-pair · gpt-3.5-turbo

    references to declassification events and related concepts in a historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     advertis
    -0.74
     Imran
    -0.67
     Beaver
    -0.66
    ħĭ
    -0.65
     Alibaba
    -0.65
     Caption
    -0.65
     Barbarian
    -0.65
     DSL
    -0.65
    lain
    -0.64
     Yelp
    -0.63
    POSITIVE LOGITS
     declass
    0.89
    20439
    0.86
    omore
    0.74
    velength
    0.73
    ãĥīãĥ©ãĤ´ãĥ³
    0.72
     remembrance
    0.71
    identally
    0.70
    reet
    0.69
    mere
    0.69
     Lyndon
    0.68
    Activations Density 0.032%

    No Known Activations