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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5231
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "Anyone"

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "Anyone."

    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
     retreat
    -0.71
     then
    -0.70
     favor
    -0.65
     favour
    -0.65
     substitute
    -0.65
     indirect
    -0.64
     term
    -0.63
     pref
    -0.61
     adjusted
    -0.61
     notes
    -0.61
    POSITIVE LOGITS
    Anyone
    3.62
     Anyone
    2.70
    Whoever
    1.72
    Someone
    1.59
     Whoever
    1.55
     anyone
    1.52
    Any
    1.47
     anybody
    1.46
    Everyone
    1.38
    Anything
    1.33
    Activations Density 0.017%

    No Known Activations