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

    Neuronpedia

    Jacobian LensNEW
    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. 20647
    Prev
    Next
    INDEX
    Explanations

    situations or attributes that are extreme or incredulous

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating exaggerated or implausible scenarios

    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
    kind
    -0.72
     largeDownload
    -0.65
    aldi
    -0.62
    updated
    -0.61
     ancest
    -0.60
    chwitz
    -0.58
    Products
    -0.57
    ARA
    -0.57
    atis
    -0.57
     Cake
    -0.56
    POSITIVE LOGITS
     withstand
    0.83
     compete
    0.80
     feas
    0.78
     contemplate
    0.78
    Fail
    0.76
     anymore
    0.75
     outweigh
    0.74
     survive
    0.74
     tolerate
    0.73
     bother
    0.73
    Activations Density 0.087%

    No Known Activations