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. 3-RES-JB
    6. 14862
    Prev
    Next
    INDEX
    Explanations

    terms related to procedural aspects or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to procedural matters and regulations

    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
    ffee
    -0.85
    jri
    -0.83
    ammad
    -0.80
    sole
    -0.79
    kers
    -0.78
    ammed
    -0.78
    ning
    -0.78
    ofi
    -0.78
    wan
    -0.77
    tub
    -0.77
    POSITIVE LOGITS
     procedural
    1.10
     safeguards
    0.92
     violations
    0.87
    izational
    0.85
     protections
    0.83
     restraints
    0.81
     rules
    0.80
     guiActiveUn
    0.78
     executions
    0.78
     requirements
    0.76
    Activations Density 0.007%

    No Known Activations