© 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. 6-RES-JB
    11. 2860
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "to" followed by another verb

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructions that begin with "just to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olor
    -0.82
    pora
    -0.76
    ascript
    -0.73
    egal
    -0.68
    anon
    -0.67
    ahead
    -0.61
    apolis
    -0.60
    upon
    -0.59
    ama
    -0.59
    later
    -0.59
    POSITIVE LOGITS
     luck
    0.82
     remind
    0.76
    cause
    0.73
     coincidence
    0.66
     reset
    0.64
     wit
    0.63
     refresh
    0.63
     piss
    0.63
     reassure
    0.62
     confuse
    0.61
    Activations Density 0.043%

    No Known Activations