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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11730
    Prev
    Next
    INDEX
    Explanations

    mentions of the Colombian drug lord Pablo Escobar

    oai_token-act-pair · gpt-3.5-turbo

    instances of the suffixes 'ador', 'obar', and 'adic' related to specific names or titles

    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
    ardy
    -0.70
    quartered
    -0.68
     pity
    -0.64
     CST
    -0.62
    racted
    -0.61
    MQ
    -0.61
     clipboard
    -0.60
    roads
    -0.59
    sheet
    -0.59
     subcontract
    -0.58
    POSITIVE LOGITS
    ably
    0.92
    idad
    0.88
    hyde
    0.87
    ienne
    0.86
    ÃŃa
    0.85
    ador
    0.85
    ians
    0.83
    illo
    0.81
    antes
    0.81
    ibles
    0.80
    Activations Density 0.011%

    No Known Activations