© 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. 6454
    Prev
    Next
    INDEX
    Explanations

    the word "pandering" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to pandas and related terms

    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
    âĸ¬
    -0.74
     Lauder
    -0.72
    terday
    -0.69
    LECT
    -0.67
    FUL
    -0.67
    pell
    -0.66
    creen
    -0.64
    ALD
    -0.63
    CLASSIFIED
    -0.63
    =#
    -0.63
    POSITIVE LOGITS
    emonium
    1.57
    emic
    1.37
    erers
    0.98
    aren
    0.93
     pand
    0.92
    ering
    0.91
    anus
    0.87
    emia
    0.86
    erer
    0.86
    erest
    0.86
    Activations Density 0.041%

    No Known Activations