© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 2839
    Prev
    Next
    INDEX
    Explanations

    mentions of specific players in a sports context, particularly discussing their performance or potential

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to player capabilities and potential in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    PDATE
    -0.80
    anamo
    -0.78
    renheit
    -0.77
    actionDate
    -0.76
     tradem
    -0.75
    Cath
    -0.74
    INESS
    -0.73
    ategory
    -0.73
     disadvant
    -0.71
    cens
    -0.69
    POSITIVE LOGITS
     thrive
    1.16
     contribute
    1.14
     flourish
    1.11
     carve
    1.11
     complement
    1.08
     latch
    1.07
     platoon
    1.06
     develop
    1.02
     elevate
    1.01
     excel
    1.01
    Activations Density 0.116%

    No Known Activations