© 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. 0-RES-JB
    11. 22734
    Prev
    Next
    INDEX
    Explanations

    the word "nominated" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nominations and endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    death
    -0.71
    Distance
    -0.69
     passage
    -0.64
    ring
    -0.63
    uring
    -0.63
    damage
    -0.61
    amine
    -0.60
     haste
    -0.60
    poll
    -0.60
     feather
    -0.59
    POSITIVE LOGITS
     endorsed
    1.97
     nominated
    1.82
     approved
    1.79
     sanctioned
    1.70
     rejected
    1.69
     indicted
    1.57
     branded
    1.54
     certified
    1.50
     embraced
    1.50
     accepted
    1.47
    Activations Density 0.029%

    No Known Activations