© 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. 0-RES-JB
    11. 4887
    Prev
    Next
    INDEX
    Explanations

    words related to traffic issues

    oai_token-act-pair · gpt-3.5-turbo

    negative emotions or experiences associated with obstacles or disruptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aura
    -0.75
     Seeking
    -0.75
    Reward
    -0.73
    imaru
    -0.66
    isa
    -0.64
     Bul
    -0.64
     Ion
    -0.63
     Funding
    -0.63
    =-=-=-=-=-=-=-=-
    -0.62
    asing
    -0.62
    POSITIVE LOGITS
     jams
    2.81
     unh
    1.60
     stopp
    1.34
     washed
    1.27
    minist
    1.20
     unl
    1.15
    glers
    1.00
     jammed
    0.97
     cant
    0.96
     jerk
    0.88
    Activations Density 0.041%

    No Known Activations