© 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. 21943
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and competitions

    oai_token-act-pair · gpt-3.5-turbo

    situations involving sports wins and losses

    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
     GOODMAN
    -0.77
    Square
    -0.74
    ATURES
    -0.74
    pees
    -0.72
    conom
    -0.68
    assian
    -0.66
    Maker
    -0.65
    coins
    -0.65
    Demand
    -0.65
    ographer
    -0.65
    POSITIVE LOGITS
     disappointing
    1.40
     relegation
    1.34
     disastrous
    1.29
     debacle
    1.27
     loss
    1.23
     setback
    1.22
     defeat
    1.21
     disappointment
    1.19
     injury
    1.19
     dismal
    1.18
    Activations Density 0.305%

    No Known Activations