© 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. 10-RES-JB
    11. 16218
    Prev
    Next
    INDEX
    Explanations

    contact information such as phone numbers and email addresses

    oai_token-act-pair · gpt-3.5-turbo

    contact information and details typically associated with news alerts or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artisan
    -0.75
    tub
    -0.67
    ersion
    -0.65
    mire
    -0.63
    cone
    -0.62
    going
    -0.62
    inventoryQuantity
    -0.61
    ulously
    -0.61
     delinquent
    -0.60
    duration
    -0.59
    POSITIVE LOGITS
    353
    1.06
    354
    1.03
    457
    1.01
    755
    1.00
    440
    0.97
     978
    0.97
    2020
    0.97
    358
    0.96
    365
    0.96
     353
    0.96
    Activations Density 0.033%

    No Known Activations