Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6902
    Prev
    Next
    INDEX
    Explanations

    threats or situations that pose a potential danger or risk

    oai_token-act-pair · gpt-3.5-turbo

    terms related to threats or dangers, particularly in a political or social context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gel
    -0.76
     linen
    -0.73
     donkey
    -0.72
     camel
    -0.70
     cycling
    -0.69
     carriage
    -0.67
    ppo
    -0.66
     bicycles
    -0.66
    atari
    -0.66
     complementary
    -0.64
    POSITIVE LOGITS
     Threat
    3.28
    threat
    3.00
     embold
    1.11
     fright
    1.10
     Resp
    0.94
    Attempts
    0.93
     hast
    0.91
     Hast
    0.90
    vironment
    0.88
     Stun
    0.87
    Activations Density 0.040%

    No Known Activations