© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 11374
    Prev
    Next
    INDEX
    Explanations

    the word "boxes" with a strong activation value

    oai_token-act-pair · gpt-3.5-turbo

    references to physical containers

    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
    Filename
    -0.79
    noon
    -0.73
    nee
    -0.72
    irgin
    -0.71
     Bald
    -0.71
     Archdemon
    -0.67
    DEM
    -0.67
    00200000
    -0.67
    iour
    -0.65
    nesota
    -0.65
    POSITIVE LOGITS
     boxes
    1.43
    hops
    1.21
    boxes
    1.15
    mith
    1.13
     crates
    0.91
     containers
    0.89
    poons
    0.87
     box
    0.85
    pec
    0.85
    pots
    0.85
    Activations Density 0.009%

    No Known Activations