© 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. 9529
    Prev
    Next
    INDEX
    Explanations

    words related to beef or beef-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of beef as both a food item and a context for conflicts or discussions

    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¬
    -0.85
    pmwiki
    -0.72
    ISTER
    -0.69
    uyomi
    -0.67
     Archangel
    -0.66
    SPONSORED
    -0.64
    âĸ¬âĸ¬
    -0.60
     Devices
    -0.60
    hematic
    -0.60
     Spac
    -0.60
    POSITIVE LOGITS
    cake
    1.23
    ington
    1.02
     jer
    0.98
    skin
    0.91
    keyes
    0.88
    ishly
    0.86
    ste
    0.84
    riter
    0.84
    asted
    0.83
    cakes
    0.83
    Activations Density 0.025%

    No Known Activations