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. 19553
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal investigations and government actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to political investigations and charges

    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
     âĨ
    -0.61
     :=
    -0.53
     FANTASY
    -0.49
     Texture
    -0.48
     Nerd
    -0.47
     Streaming
    -0.46
     rejoice
    -0.46
     Morty
    -0.46
     sucks
    -0.45
     âĶľâĶĢâĶĢ
    -0.45
    POSITIVE LOGITS
     vetted
    0.57
     unconstitutional
    0.56
     negotiating
    0.56
     vetting
    0.56
     consulate
    0.55
     diplomatic
    0.55
     constitutional
    0.54
    authorized
    0.54
     allegiance
    0.53
     incrim
    0.52
    Activations Density 3.561%

    No Known Activations