© 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. 7588
    Prev
    Next
    INDEX
    Explanations

    rank and military titles

    oai_token-act-pair · gpt-3.5-turbo

    titles and ranks of military personnel

    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
    SourceFile
    -0.83
    Consumer
    -0.68
    âĹ¼
    -0.67
    Story
    -0.66
    spir
    -0.64
    Tree
    -0.64
    jury
    -0.64
    rums
    -0.63
    apers
    -0.62
    consumer
    -0.62
    POSITIVE LOGITS
     Mattis
    1.14
    anamo
    1.00
     Kham
    0.88
     Eisenhower
    0.88
     Hasan
    0.86
    onnaissance
    0.84
    dinand
    0.83
     Ernest
    0.82
    utenant
    0.80
     commanding
    0.79
    Activations Density 0.063%

    No Known Activations