© 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. 2533
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific product or brand, possibly related to technology or sports

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific energetic product or topic related to electric vehicles

    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
    asio
    -0.78
    orial
    -0.75
    rador
    -0.71
    istas
    -0.71
    ãĤ¢ãĥ«
    -0.70
    orship
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.70
    Downloadha
    -0.69
    raints
    -0.69
    iesta
    -0.69
    POSITIVE LOGITS
    LE
    1.29
    IGH
    1.14
    VEL
    1.00
    BO
    1.00
    OVER
    0.98
    WOOD
    0.96
    ASE
    0.91
    PE
    0.91
    lla
    0.89
    LOAD
    0.89
    Activations Density 0.005%

    No Known Activations