© 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. 3114
    Prev
    Next
    INDEX
    Explanations

    technical terms related to video and image frames

    oai_token-act-pair · gpt-3.5-turbo

    references to frames in the context of gaming, animation, or video

    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
    IUM
    -0.72
    inav
    -0.72
    iability
    -0.71
    ities
    -0.71
    BAT
    -0.69
    ité
    -0.68
    inen
    -0.68
    iott
    -0.68
    iant
    -0.66
    icably
    -0.66
    POSITIVE LOGITS
    buffer
    1.37
    border
    1.00
    buff
    0.98
    builder
    0.91
    builders
    0.83
    Rate
    0.81
    hog
    0.80
    asus
    0.76
    buster
    0.75
    perfect
    0.75
    Activations Density 0.040%

    No Known Activations