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. 2-RES-JB
    6. 20379
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or policy issues, particularly ones that are unconstitutional

    oai_token-act-pair · gpt-3.5-turbo

    terms related to unconstitutional practices or laws

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igi
    -0.85
    erm
    -0.77
    ynthesis
    -0.73
    VIS
    -0.73
    orah
    -0.73
     Tycoon
    -0.72
    opic
    -0.71
    á
    -0.71
    Merc
    -0.69
    dain
    -0.68
    POSITIVE LOGITS
     unconstitutional
    0.95
     overr
    0.80
     unfocusedRange
    0.76
     constitutional
    0.74
     violations
    0.74
     guiActiveUn
    0.69
     usur
    0.69
     violation
    0.67
     overturned
    0.67
     Tanz
    0.67
    Activations Density 0.011%

    No Known Activations