© 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. 4-RES-JB
    11. 22296
    Prev
    Next
    INDEX
    Explanations

    phrases related to research participants

    oai_token-act-pair · gpt-3.5-turbo

    references to study participants

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

    No Comments

    Negative Logits
     vengeance
    -0.69
     thicker
    -0.62
    vell
    -0.62
     Sect
    -0.61
     Manor
    -0.59
     supremacy
    -0.58
    stones
    -0.58
     Bale
    -0.58
     clich
    -0.57
     Shack
    -0.56
    POSITIVE LOGITS
    cript
    0.90
     Participants
    0.88
     participant
    0.82
    particip
    0.80
    essee
    0.79
     participants
    0.77
    ividual
    0.76
    nels
    0.75
    uates
    0.74
    hips
    0.74
    Activations Density 0.018%

    No Known Activations