© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RES-JB
    11. 17535
    Prev
    Next
    INDEX
    Explanations

    contact information, specifically phone numbers to call for a variety of purposes

    oai_token-act-pair · gpt-3.5-turbo

    phone numbers and contact information for various services and authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sic
    -0.65
    agy
    -0.64
    iris
    -0.61
     WATCHED
    -0.61
    prototype
    -0.60
    worthiness
    -0.60
    gow
    -0.58
     Tycoon
    -0.58
    chains
    -0.58
    æѦ
    -0.57
    POSITIVE LOGITS
     416
    1.22
     407
    1.21
     415
    1.21
     410
    1.19
     503
    1.19
     510
    1.18
     702
    1.18
     323
    1.17
     970
    1.17
     504
    1.17
    Activations Density 0.072%

    No Known Activations