Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 24337
    Prev
    Next
    INDEX
    Explanations

    features and characteristics of products or items, such as amenities, functionalities, and attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to items or features associated with amenities or utilities

    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
    ['
    -0.72
    00007
    -0.71
    References
    -0.70
    conn
    -0.67
     è£ıè
    -0.67
     bothers
    -0.67
    failed
    -0.66
     externalToEVAOnly
    -0.64
    gray
    -0.64
    reports
    -0.64
    POSITIVE LOGITS
     perfect
    1.05
     yours
    1.03
     FREE
    1.00
     ideal
    0.99
     available
    0.98
     packed
    0.98
     proud
    0.96
     ready
    0.95
     designed
    0.95
     guaranteed
    0.94
    Activations Density 0.227%

    No Known Activations