© 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. 3-RES-JB
    11. 1902
    Prev
    Next
    INDEX
    Explanations

    words related to impactful events or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Impact" and related concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izational
    -0.91
    isations
    -0.89
    achy
    -0.86
    isms
    -0.79
    ulators
    -0.78
    asp
    -0.78
    izations
    -0.78
    ulates
    -0.77
    ormal
    -0.76
    ching
    -0.75
    POSITIVE LOGITS
     Fail
    0.93
     Bound
    0.91
     Points
    0.89
     Fighting
    0.88
     Libre
    0.86
     Zone
    0.86
     Labs
    0.86
     Breaker
    0.85
     Control
    0.85
     Wrestling
    0.85
    Activations Density 0.060%

    No Known Activations