© 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. 23799
    Prev
    Next
    INDEX
    Explanations

    words related to travel and transportation

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and various forms of the word "and."

    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
     Bor
    -0.76
     Diesel
    -0.73
     Loren
    -0.69
    pher
    -0.66
    YL
    -0.66
    tek
    -0.66
    zan
    -0.65
    geons
    -0.65
    seless
    -0.64
    é¾
    -0.64
    POSITIVE LOGITS
     deletion
    0.95
     acquisition
    0.93
     acquisitions
    0.86
     retention
    0.84
     delet
    0.82
     destination
    0.81
     colonization
    0.81
     departures
    0.80
     departure
    0.79
     dismissal
    0.77
    Activations Density 0.296%

    No Known Activations