© 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 EvalsExportsinterp-engineNEWAPI 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. 1113
    Prev
    Next
    INDEX
    Explanations

    mentions of specific smartphone models

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific smartphone brands and models

    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
    hov
    -0.91
    pee
    -0.89
    nels
    -0.88
    race
    -0.82
    ipel
    -0.77
    isode
    -0.76
    ettlement
    -0.75
    yip
    -0.75
    utherford
    -0.75
    jri
    -0.75
    POSITIVE LOGITS
     Corporation
    0.91
     OEM
    0.79
     Snapdragon
    0.79
     Siem
    0.79
     Electronics
    0.79
     Mobility
    0.78
     phones
    0.78
     handset
    0.78
     Corp
    0.76
     Lumia
    0.76
    Activations Density 0.033%

    No Known Activations