© 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. 7-RES-JB
    11. 5278
    Prev
    Next
    INDEX
    Explanations

    mentions of strong beliefs or interests in particular topics or causes

    oai_token-act-pair · gpt-3.5-turbo

    references to beliefs and values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fle
    -0.62
    veland
    -0.60
     Jol
    -0.60
    Missing
    -0.59
     Zup
    -0.59
    odder
    -0.59
    vier
    -0.58
    phe
    -0.57
    installed
    -0.55
    ussen
    -0.55
    POSITIVE LOGITS
     spirituality
    0.75
     pursuits
    0.75
     virtues
    0.75
     ideals
    0.75
     enthus
    0.75
     deities
    0.74
     deity
    0.74
     arts
    0.73
     fundamentals
    0.72
     rhythms
    0.71
    Activations Density 0.648%

    No Known Activations