© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20490
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential achievement or success

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential outcomes or candidates in competitive situations

    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
     Warning
    -0.74
    quickShipAvailable
    -0.74
     Conversation
    -0.72
     Concern
    -0.70
    enforcement
    -0.68
     Perspective
    -0.67
    problem
    -0.66
     restraints
    -0.65
     Flex
    -0.63
     Caller
    -0.63
    POSITIVE LOGITS
     win
    1.46
     succeed
    1.45
     overtake
    1.42
     clinch
    1.35
     qualify
    1.33
     earn
    1.31
     become
    1.31
     topple
    1.28
     compete
    1.27
     surpass
    1.26
    Activations Density 0.234%

    No Known Activations