© 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. 8-RES-JB
    11. 20440
    Prev
    Next
    INDEX
    Explanations

    phrases related to hidden information or secrets

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or concepts related to societal issues and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    psey
    -0.59
    nered
    -0.58
    ividual
    -0.58
    enegger
    -0.55
    ctors
    -0.55
    quartered
    -0.53
    arling
    -0.52
     Tanz
    -0.52
    ogie
    -0.50
     performing
    -0.50
    POSITIVE LOGITS
     happening
    0.88
     fruition
    0.72
     undone
    0.70
     happen
    0.70
     occurring
    0.68
     underway
    0.67
     hinges
    0.58
     reverber
    0.57
     occur
    0.56
     imminent
    0.56
    Activations Density 0.634%

    No Known Activations