© 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. 2-RES-JB
    6. 23938
    Prev
    Next
    INDEX
    Explanations

    instances of people wearing T-shirts with specific words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to T-shirts and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     distant
    -0.69
     presided
    -0.66
    Reviewer
    -0.66
    «ĺ
    -0.64
    20439
    -0.63
    judicial
    -0.63
    ruciating
    -0.62
    ntil
    -0.60
    audi
    -0.60
     Trem
    -0.59
    POSITIVE LOGITS
    shirt
    1.41
    shirts
    1.24
    hirt
    1.02
     shirts
    1.01
    idas
    0.92
     shirt
    0.91
    boy
    0.86
     Shirt
    0.86
    leeve
    0.85
    cloth
    0.84
    Activations Density 0.006%

    No Known Activations