© 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. 9-RES-JB
    11. 7565
    Prev
    Next
    INDEX
    Explanations

    phrases related to prevention or avoiding negative outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prevention and protective measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.78
    ammy
    -0.78
    bard
    -0.77
    enegger
    -0.77
    framework
    -0.77
    spirit
    -0.75
    sonian
    -0.74
    bold
    -0.73
    æ©
    -0.71
    lene
    -0.70
    POSITIVE LOGITS
    ative
    1.00
     regress
    0.98
     duplication
    0.97
     accidental
    0.95
     detection
    0.94
     accidents
    0.93
     disasters
    0.92
     future
    0.91
     deterioration
    0.90
     misunderstand
    0.90
    Activations Density 0.054%

    No Known Activations