© 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. 11-RES-JB
    11. 4060
    Prev
    Next
    INDEX
    Explanations

    cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating community support and social initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    politics
    -0.77
    ciples
    -0.75
    soType
    -0.71
    etheless
    -0.70
     cryptocurrencies
    -0.68
    nature
    -0.67
    Topics
    -0.66
    respective
    -0.65
    then
    -0.64
     endif
    -0.64
    POSITIVE LOGITS
     famously
    1.01
     recently
    0.95
     example
    0.85
     illustrates
    0.83
     recounted
    0.81
     experimented
    0.80
     demonstrated
    0.76
    example
    0.74
     pioneered
    0.73
     bombed
    0.72
    Activations Density 0.655%

    No Known Activations