© 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. 16056
    Prev
    Next
    INDEX
    Explanations

    venues and locations where events take place

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports locations and events

    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
     enumer
    -0.80
    jriwal
    -0.74
     campaigner
    -0.72
    acters
    -0.71
    doms
    -0.70
    earchers
    -0.69
    utenberg
    -0.69
    eanor
    -0.69
    phabet
    -0.67
    dyl
    -0.67
    POSITIVE LOGITS
     Stadium
    1.86
     Coliseum
    1.42
     Arena
    1.41
     stadium
    1.37
    Aren
    1.28
     stadiums
    1.17
     Dome
    1.16
     Speedway
    1.09
     Bowl
    1.09
     Pavilion
    1.05
    Activations Density 0.184%

    No Known Activations