© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7614
    Prev
    Next
    INDEX
    Explanations

    phrases related to policies, regulations, and government actions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to healthcare policy 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
     mysterious
    -0.88
     unlucky
    -0.83
     thrill
    -0.83
     mystery
    -0.80
     curiosity
    -0.79
     paranormal
    -0.79
     unexplained
    -0.78
     fandom
    -0.78
     hairs
    -0.78
     psychic
    -0.76
    POSITIVE LOGITS
    Economic
    1.30
    Labor
    1.30
    Govern
    1.29
    Policy
    1.28
    Government
    1.28
    WASHINGTON
    1.26
    Recommend
    1.23
    TPP
    1.23
    HUD
    1.22
    Econom
    1.21
    Activations Density 0.665%

    No Known Activations