© 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. 2-RES-JB
    11. 17588
    Prev
    Next
    INDEX
    Explanations

    references to ISO standards

    oai_token-act-pair · gpt-3.5-turbo

    references to ISO standards and certifications

    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
    hips
    -0.88
    bones
    -0.85
    eez
    -0.82
    lain
    -0.80
    bone
    -0.80
    taboola
    -0.78
    some
    -0.77
    bear
    -0.77
    packs
    -0.75
    liest
    -0.72
    POSITIVE LOGITS
    ISO
    1.07
     ISO
    1.07
    iso
    0.91
     Skydragon
    0.76
     mosqu
    0.73
     iso
    0.72
    Hunt
    0.72
    terness
    0.71
     OCT
    0.69
    FILE
    0.69
    Activations Density 0.009%

    No Known Activations