© 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. 10-RES-JB
    11. 12654
    Prev
    Next
    INDEX
    Explanations

    phrases related to political beliefs

    oai_token-act-pair · gpt-3.5-turbo

    complete sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     satell
    -0.84
     landfall
    -0.81
     orbital
    -0.80
     deton
    -0.80
     greenhouse
    -0.76
     electr
    -0.76
     predecessor
    -0.74
     glim
    -0.71
     emission
    -0.70
     stabil
    -0.70
    POSITIVE LOGITS
     They
    1.83
     Their
    1.74
     Others
    1.66
     Often
    1.64
     Sometimes
    1.55
     Occasionally
    1.50
     Many
    1.46
     Usually
    1.44
    They
    1.44
     Some
    1.40
    Activations Density 0.382%

    No Known Activations