© 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. 8-RES-JB
    11. 2483
    Prev
    Next
    INDEX
    Explanations

    data formats such as codes and versions, specifically indicated by the character "Ċ"

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ledged
    -0.70
    stellar
    -0.68
    negie
    -0.64
    ulus
    -0.61
    iates
    -0.61
    uten
    -0.60
    ogi
    -0.60
    itance
    -0.60
    iations
    -0.58
    lihood
    -0.58
    POSITIVE LOGITS
    hello
    1.06
    Posted
    0.94
    Updated
    0.94
    ccording
    0.82
     VIDEOS
    0.79
    ³³³
    0.74
    ³³³³³³³³³³³³³³³³
    0.74
     POLITICO
    0.73
    WASHINGTON
    0.72
    BBC
    0.71
    Activations Density 0.147%

    No Known Activations