© 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. 9886
    Prev
    Next
    INDEX
    Explanations

    phrases related to prioritizing specific groups or interests above others, often involving a sense of risk or danger

    oai_token-act-pair · gpt-3.5-turbo

    topics related to American workers, jobs, and interests

    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
    Winged
    -0.65
    etheless
    -0.64
    apply
    -0.60
    oris
    -0.55
     Changed
    -0.52
     Evening
    -0.52
     Scrolls
    -0.51
     Subtle
    -0.51
     Same
    -0.51
    dict
    -0.50
    POSITIVE LOGITS
     squarely
    1.24
     ahead
    0.95
     firmly
    0.87
     into
    0.83
     closer
    0.81
     overboard
    0.81
     upside
    0.79
     atop
    0.78
     smack
    0.77
     onto
    0.77
    Activations Density 0.120%

    No Known Activations