© 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. 8-RES-JB
    11. 7003
    Prev
    Next
    INDEX
    Explanations

    phrases containing the structure "not-so"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of negative phrases or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GEAR
    -0.77
     canvas
    -0.75
     Skydragon
    -0.69
     Extensions
    -0.66
     Rouge
    -0.65
     eBook
    -0.63
     Downing
    -0.62
    icles
    -0.61
     revocation
    -0.61
    iers
    -0.60
    POSITIVE LOGITS
    yet
    1.19
    great
    1.16
    perfect
    1.09
    nice
    1.07
    named
    1.06
    quite
    1.06
    necess
    1.06
    famous
    1.05
    existent
    1.04
    successful
    1.02
    Activations Density 0.041%

    No Known Activations