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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24233
    Prev
    Next
    INDEX
    Explanations

    words related to safety or potential danger

    oai_token-act-pair · gpt-3.5-turbo

    words related to safety and danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sis
    -0.63
     occasional
    -0.61
     essays
    -0.61
    storms
    -0.61
     elusive
    -0.61
     Winged
    -0.58
     Honour
    -0.57
     Kinnikuman
    -0.57
     ethn
    -0.57
     sails
    -0.56
    POSITIVE LOGITS
    afe
    1.21
    terness
    0.94
    becue
    0.91
    zzle
    0.87
    ctuary
    0.86
    afa
    0.85
    ffe
    0.84
    eteria
    0.83
    cakes
    0.83
    yip
    0.79
    Activations Density 0.004%

    No Known Activations