© 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. 1-RES-JB
    11. 10467
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific topic, potentially related to a specific anime or game title

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "og" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.77
    IDENT
    -0.72
     culture
    -0.62
     rightful
    -0.61
     Michaels
    -0.60
     Reagan
    -0.60
    wcs
    -0.60
     Kimmel
    -0.59
     breast
    -0.59
    riott
    -0.57
    POSITIVE LOGITS
    og
    1.44
    ogo
    1.13
    ogg
    1.11
    ogs
    1.02
    gers
    1.01
    roup
    0.99
    ues
    0.99
    gy
    0.96
    omb
    0.96
    agate
    0.94
    Activations Density 0.008%

    No Known Activations