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. 3-RES-JB
    6. 9855
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions, particularly those involving restrictions or secrecy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legal restrictions or gag orders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.77
     Hurricanes
    -0.76
    undai
    -0.66
     Blessed
    -0.65
    ģ«
    -0.64
     cryst
    -0.63
    accompan
    -0.62
     redistributed
    -0.62
    ept
    -0.61
     paved
    -0.60
    POSITIVE LOGITS
    glers
    1.32
     gag
    1.07
     reel
    0.91
    bag
    0.90
    bags
    0.86
    gers
    0.86
     reflex
    0.84
    eries
    0.84
    liest
    0.81
    oon
    0.79
    Activations Density 0.006%

    No Known Activations