© 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. 20671
    Prev
    Next
    INDEX
    Explanations

    phrases related to competition and victory

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to winning or achieving success

    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
     BaseType
    -0.76
    soDeliveryDate
    -0.62
     Habit
    -0.62
    regation
    -0.60
     propagation
    -0.59
    GY
    -0.59
     SetTextColor
    -0.58
    Types
    -0.58
    ATIONAL
    -0.58
     translation
    -0.57
    POSITIVE LOGITS
     victorious
    1.47
     vict
    1.20
     triumphant
    1.16
     unsc
    1.08
     stronger
    1.04
     unprepared
    1.00
     disappointed
    0.98
     undefeated
    0.98
     smelling
    0.97
     confident
    0.97
    Activations Density 0.139%

    No Known Activations