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. 11-RES-JB
    6. 4382
    Prev
    Next
    INDEX
    Explanations

    action-related words regarding criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    actions related to events, particularly involving the capturing, selling, or legal status of individuals or materials

    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
    quickShipAvailable
    -0.60
    âĶĢâĶĢâĶĢâĶĢ
    -0.56
     Anger
    -0.56
     VIDEO
    -0.55
     Razer
    -0.55
    cipled
    -0.54
    erity
    -0.54
    othy
    -0.54
    Leader
    -0.54
     Ratt
    -0.53
    POSITIVE LOGITS
     annually
    1.15
     apiece
    1.04
     worldwide
    1.02
     statewide
    1.00
     consecut
    0.98
     nationwide
    0.97
     globally
    0.97
     since
    0.90
     yearly
    0.90
    ogether
    0.89
    Activations Density 0.263%

    No Known Activations