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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 21173
    Prev
    Next
    INDEX
    Explanations

    words related to protection, insulation, and shielding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of protection or shielding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onde
    -0.70
     Kinn
    -0.69
    orne
    -0.66
    NC
    -0.65
    TPP
    -0.64
    OTA
    -0.61
    itled
    -0.61
    acher
    -0.60
    apest
    -0.60
    leaf
    -0.60
    POSITIVE LOGITS
    ively
    0.87
     protects
    0.85
     against
    0.83
    ously
    0.81
    ailability
    0.80
    iveness
    0.80
     shielding
    0.79
     protecting
    0.76
    against
    0.75
     detection
    0.75
    Activations Density 0.099%

    No Known Activations