© 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. 1-RES-JB
    11. 23123
    Prev
    Next
    INDEX
    Explanations

    names of soccer players

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igslist
    -0.77
    clair
    -0.74
    avez
    -0.71
     CPC
    -0.71
    displayText
    -0.69
    awaru
    -0.66
    nels
    -0.66
     hill
    -0.64
    ebin
    -0.63
     sworn
    -0.62
    POSITIVE LOGITS
     Gareth
    1.33
     Bale
    1.21
    areth
    1.11
     Isa
    0.85
     Evans
    0.80
     Aires
    0.80
     Davies
    0.77
    warm
    0.75
     Edwards
    0.74
    bane
    0.73
    Activations Density 0.009%

    No Known Activations