© 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. 0-RES-JB
    11. 1795
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific location, "Portsmouth."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "mouth" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     simpler
    -0.69
     updated
    -0.68
     Ars
    -0.65
     Suk
    -0.60
     ev
    -0.60
     updating
    -0.58
     xml
    -0.58
     Relic
    -0.58
     remedies
    -0.58
     simple
    -0.57
    POSITIVE LOGITS
    mouth
    5.38
     Mouth
    1.85
     mouth
    1.47
     mouths
    1.36
    butt
    1.00
    chester
    0.99
    croft
    0.98
    emouth
    0.97
    minster
    0.97
    geon
    0.95
    Activations Density 0.008%

    No Known Activations