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. 7-RES-JB
    6. 15417
    Prev
    Next
    INDEX
    Explanations

    names related to politics and possibly regions

    oai_token-act-pair · gpt-3.5-turbo

    references to the individual Hosni Mubarak

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iences
    -0.88
    trap
    -0.85
    ienced
    -0.84
    ansas
    -0.84
    bats
    -0.80
    ioned
    -0.79
    lishes
    -0.79
    ullivan
    -0.76
    inventoryQuantity
    -0.75
    imental
    -0.72
    POSITIVE LOGITS
    atal
    0.86
    elsen
    0.85
    emi
    0.84
    unci
    0.83
    uclear
    0.76
    ocular
    0.74
    ounced
    0.74
    Äį
    0.73
    acht
    0.72
     Angle
    0.70
    Activations Density 0.025%

    No Known Activations