© 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. 11-RES-JB
    11. 7648
    Prev
    Next
    INDEX
    Explanations

    words related to video technology

    oai_token-act-pair · gpt-3.5-turbo

    terms related to video and graphics technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Masonic
    -0.79
    arity
    -0.79
    vic
    -0.75
    ishable
    -0.74
    wed
    -0.74
    cies
    -0.71
    lesiastical
    -0.70
    erella
    -0.69
    xual
    -0.68
    aneous
    -0.67
    POSITIVE LOGITS
     codec
    1.33
     playback
    1.24
     Codec
    1.14
     decoding
    1.10
     adapter
    1.03
     processor
    1.02
     adapters
    1.01
     streaming
    1.00
     decode
    1.00
     processors
    0.99
    Activations Density 0.135%

    No Known Activations