Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 1883
    Prev
    Next
    INDEX
    Explanations

    references to formal organizations or establishments

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions, particularly in an educational or organizational context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gets
    -0.74
     Powder
    -0.72
    THER
    -0.71
    bid
    -0.66
     Rockies
    -0.65
     sled
    -0.63
    DEN
    -0.62
    PO
    -0.61
    patch
    -0.61
    Timer
    -0.60
    POSITIVE LOGITS
    itutional
    1.03
     institution
    1.02
    utions
    0.99
     institutions
    0.98
     Institution
    0.89
    arians
    0.85
    ually
    0.82
    rity
    0.79
    establishment
    0.78
    itute
    0.77
    Activations Density 0.015%

    No Known Activations