© 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. 6-RES-JB
    11. 10650
    Prev
    Next
    INDEX
    Explanations

    business-related terms and phrases such as pricing, shipping, and sales

    oai_token-act-pair · gpt-3.5-turbo

    information about event pricing and acceptance policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼
    -0.79
    æĺ
    -0.77
    fork
    -0.76
    derived
    -0.76
    arthed
    -0.75
    weak
    -0.73
    Thumbnail
    -0.73
    Suddenly
    -0.72
    blance
    -0.71
    ghazi
    -0.71
    POSITIVE LOGITS
     reservations
    0.87
     ONLY
    0.85
     NEC
    0.81
     reservation
    0.79
     booked
    0.79
     Continental
    0.77
     purchase
    0.77
     rentals
    0.77
     reserved
    0.76
     unlimited
    0.76
    Activations Density 0.548%

    No Known Activations