© 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. 8-RES-JB
    11. 4593
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of risk or endangerment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to risk and danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dies
    -0.77
    essee
    -0.74
    eve
    -0.74
    geist
    -0.72
    LINE
    -0.71
    speak
    -0.70
    aters
    -0.69
    ocations
    -0.68
    elf
    -0.67
    sama
    -0.67
    POSITIVE LOGITS
     losing
    0.91
     extinction
    0.90
     exposing
    0.86
     jeopard
    0.81
     risking
    0.81
     endanger
    0.78
    lessly
    0.77
     sacrificing
    0.76
     ruining
    0.76
     starvation
    0.75
    Activations Density 0.055%

    No Known Activations