© 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. 7050
    Prev
    Next
    INDEX
    Explanations

    references to the specific term "Box"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific 'Box' categories or labels

    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
    ittee
    -0.83
    ufact
    -0.80
    puter
    -0.78
    merce
    -0.75
    FUL
    -0.70
    asury
    -0.69
    ptoms
    -0.67
    opoulos
    -0.66
     beh
    -0.65
     CSI
    -0.65
    POSITIVE LOGITS
    es
    1.07
     Box
    1.01
    er
    0.98
    Box
    0.97
    wra
    0.97
    esy
    0.97
    sets
    0.96
    boxes
    0.94
    eers
    0.94
    box
    0.93
    Activations Density 0.012%

    No Known Activations