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. 3877
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal protections or rights

    oai_token-act-pair · gpt-3.5-turbo

    references to legal and social protections

    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
     istg
    -0.65
    oca
    -0.61
    iche
    -0.60
    NAS
    -0.59
    ravis
    -0.59
    bus
    -0.58
     pulp
    -0.58
     tires
    -0.58
    Sus
    -0.57
     Stain
    -0.57
    POSITIVE LOGITS
     protections
    1.10
     enshr
    1.06
     afforded
    0.93
     safeguards
    0.86
     Rights
    0.77
     guaranteeing
    0.77
    protect
    0.73
     protecting
    0.71
     Ambro
    0.71
    rights
    0.70
    Activations Density 0.034%

    No Known Activations