© 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. 10-RES-JB
    11. 11323
    Prev
    Next
    INDEX
    Explanations

    instances where elements appear in both the front and back of something

    oai_token-act-pair · gpt-3.5-turbo

    references to positions or locations in diagrams or descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Deal
    -0.78
    TIME
    -0.77
    76561
    -0.76
    EStream
    -0.70
    faith
    -0.68
    Time
    -0.67
    Merit
    -0.67
    ãĥīãĥ©
    -0.66
    Hero
    -0.65
    ãģ®éŃĶ
    -0.65
    POSITIVE LOGITS
     underside
    1.63
     bottom
    1.48
     exterior
    1.33
     rear
    1.31
     interior
    1.29
     sides
    1.29
     upper
    1.28
     corners
    1.25
     outer
    1.24
    bottom
    1.23
    Activations Density 0.211%

    No Known Activations