© 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. 10088
    Prev
    Next
    INDEX
    Explanations

    references to different political and military entities or groups

    oai_token-act-pair · gpt-3.5-turbo

    references to the People’s Army and related entities

    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
    rawdownloadcloneembedreportprint
    -0.74
    ornia
    -0.73
    cial
    -0.73
    itous
    -0.73
    ahime
    -0.72
    ials
    -0.71
    illac
    -0.70
    nces
    -0.69
    ifi
    -0.69
    antic
    -0.68
    POSITIVE LOGITS
    å¦
    0.62
    ongyang
    0.62
     Progress
    0.60
     Pengu
    0.58
    å¿
    0.58
     Ming
    0.56
     Juda
    0.56
     Revolutionary
    0.56
     Grab
    0.56
     garrison
    0.55
    Activations Density 0.151%

    No Known Activations