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. 8-RES-JB
    6. 12033
    Prev
    Next
    INDEX
    Explanations

    phrases related to protection or defense

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating protection or defense against various threats

    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
    SPONSORED
    -0.75
    ftime
    -0.74
    Switch
    -0.69
    arse
    -0.69
    Clar
    -0.67
    video
    -0.67
    hops
    -0.66
    leaf
    -0.66
    arity
    -0.65
    isms
    -0.65
    POSITIVE LOGITS
     harm
    0.99
     impending
    0.89
     danger
    0.88
     future
    0.87
     predators
    0.86
     detection
    0.85
     extinction
    0.85
     tyranny
    0.84
     prosecution
    0.83
     undue
    0.83
    Activations Density 0.124%

    No Known Activations