© 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. 0-RES-JB
    6. 2535
    Prev
    Next
    INDEX
    Explanations

    references to various food items or brands, particularly desserts and medical conditions like "headache"

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical discomfort or pain

    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
     Ballard
    -0.65
     potent
    -0.65
     stellar
    -0.64
     Wall
    -0.63
     nationally
    -0.61
     Rutgers
    -0.61
     relevant
    -0.61
     nifty
    -0.60
     video
    -0.60
     suburb
    -0.60
    POSITIVE LOGITS
    ache
    4.77
    aches
    2.46
    ACH
    1.52
    ached
    1.50
    aching
    1.46
    acher
    1.43
    ach
    1.36
    achers
    1.26
    acho
    1.20
    ace
    1.05
    Activations Density 0.008%

    No Known Activations