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. 19779
    Prev
    Next
    INDEX
    Explanations

    groups of people or characters, often associated with a specific location or profession

    oai_token-act-pair · gpt-3.5-turbo

    the main character and their journey in various stories

    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
    soType
    -0.91
    ascript
    -0.88
    Newsletter
    -0.88
     VIDEOS
    -0.88
    utra
    -0.87
    ews
    -0.86
     Flavoring
    -0.86
    inventoryQuantity
    -0.85
    iew
    -0.85
    ItemTracker
    -0.82
    POSITIVE LOGITS
     mysterious
    1.14
     rebellious
    1.13
     teenage
    1.13
     kidnapped
    1.13
     protagonist
    1.12
     dysfunctional
    1.12
     heroine
    1.12
     conn
    1.07
     mercenary
    1.07
     vigilante
    1.07
    Activations Density 0.328%

    No Known Activations