© 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. 1-RES-JB
    11. 3598
    Prev
    Next
    INDEX
    Explanations

    names related to traffic or file upload services

    oai_token-act-pair · gpt-3.5-turbo

    words related to traffic and online file sharing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.86
     Barrett
    -0.71
    opens
    -0.69
     Hus
    -0.68
    OWS
    -0.66
     Franks
    -0.64
     Buffett
    -0.64
     Bash
    -0.63
     Schmidt
    -0.63
     Ryder
    -0.63
    POSITIVE LOGITS
    ffic
    0.93
    imedia
    0.88
    isitions
    0.80
     veter
    0.80
    edia
    0.78
     confir
    0.75
    kefeller
    0.75
    etitive
    0.74
    itbart
    0.74
     condu
    0.73
    Activations Density 0.035%

    No Known Activations