© 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. 7-RES-JB
    11. 22839
    Prev
    Next
    INDEX
    Explanations

    quotes or expressions followed by a phrase expressing an opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the act of quoting or stating opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hift
    -0.77
    ppa
    -0.73
    IELD
    -0.66
    OUND
    -0.64
     Flavoring
    -0.62
    AAA
    -0.61
    ept
    -0.59
     Explosion
    -0.59
     Insect
    -0.58
    inite
    -0.56
    POSITIVE LOGITS
     bluntly
    0.94
    self
    0.84
     succinct
    0.81
     sarcast
    0.76
    chy
    0.69
    unes
    0.68
    alian
    0.66
    selves
    0.66
    zb
    0.65
    MpServer
    0.65
    Activations Density 0.052%

    No Known Activations