© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20380
    Prev
    Next
    INDEX
    Explanations

    information about exclusive, limited edition, collector's items with specific details like edition numbers and contents

    oai_token-act-pair · gpt-3.5-turbo

    specific editions of collectible items, especially in limited quantities

    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
    ruciating
    -0.87
     behavi
    -0.76
     sluggish
    -0.75
     congest
    -0.73
    ulty
    -0.73
     eru
    -0.72
    vernment
    -0.70
     kilometres
    -0.70
    ratom
    -0.69
    Lear
    -0.68
    POSITIVE LOGITS
     Includes
    1.26
     Deluxe
    1.24
     Bundle
    1.23
    Limited
    1.18
    Includes
    1.17
     priced
    1.16
     Accessories
    1.13
     Retail
    1.12
     Included
    1.11
     Limited
    1.10
    Activations Density 0.698%

    No Known Activations