© 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. 10-RES-JB
    6. 11464
    Prev
    Next
    INDEX
    Explanations

    seek out words related to colors

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Turkey" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Opportunity
    -0.66
     [&
    -0.65
    urance
    -0.64
     Integrity
    -0.63
     moons
    -0.62
     Unch
    -0.60
     newsletters
    -0.60
     Holmes
    -0.59
    Constructed
    -0.59
     Competitive
    -0.58
    POSITIVE LOGITS
    moil
    1.45
    kish
    1.24
    geon
    1.19
    ban
    1.16
    bid
    1.15
    fing
    1.12
    rible
    1.10
    bul
    1.10
    keys
    1.10
    ismo
    1.05
    Activations Density 0.020%

    No Known Activations