© 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. 4-RES-JB
    11. 10483
    Prev
    Next
    INDEX
    Explanations

    references to items related to carrying belongings, such as backpacks and suitcases

    oai_token-act-pair · gpt-3.5-turbo

    references to bags and outdoor equipment

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

    No Comments

    Negative Logits
    flies
    -0.79
    relation
    -0.76
    oshenko
    -0.75
    inic
    -0.71
    stood
    -0.70
    isions
    -0.67
    isy
    -0.67
     devils
    -0.66
    nec
    -0.66
    rors
    -0.65
    POSITIVE LOGITS
    pole
    0.85
    packs
    0.84
    Accessory
    0.82
    packing
    0.81
     backpack
    0.81
    halla
    0.81
    pack
    0.79
    ers
    0.79
    hari
    0.76
     Sack
    0.74
    Activations Density 0.024%

    No Known Activations