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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 17315
    Prev
    Next
    INDEX
    Explanations

    phrases related to rules, regulations, and enforcement

    oai_token-act-pair · gpt-3.5-turbo

    content related to authority and regulations

    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
    neath
    -0.68
    Registered
    -0.64
     nutshell
    -0.64
    âĵĺ
    -0.63
    llers
    -0.62
     Trilogy
    -0.61
     Twins
    -0.59
    nova
    -0.58
     Kinnikuman
    -0.58
    =""
    -0.58
    POSITIVE LOGITS
     deemed
    1.03
     deem
    0.87
     warranted
    0.85
     threat
    0.84
     deems
    0.84
     jeopard
    0.83
     threatened
    0.83
     threats
    0.83
     endanger
    0.83
     reasonably
    0.81
    Activations Density 0.747%

    No Known Activations