© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 2536
    Prev
    Next
    INDEX
    Explanations

    entities related to specific regions or countries

    oai_token-act-pair · gpt-3.5-turbo

    the plural form of the letter "s"

    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
    yz
    -0.82
    bear
    -0.75
    Å¡
    -0.74
    break
    -0.70
    uscript
    -0.70
    OIL
    -0.69
    trace
    -0.69
    apego
    -0.69
    ersed
    -0.68
    ..................
    -0.68
    POSITIVE LOGITS
     own
    1.22
     reputation
    1.01
     plight
    0.94
     predecessor
    0.94
     playbook
    0.91
     existence
    0.89
     demise
    0.88
     inaugural
    0.88
     inability
    0.87
     predicament
    0.86
    Activations Density 0.196%

    No Known Activations