© 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. 22980
    Prev
    Next
    INDEX
    Explanations

    phrases indicating association or connection between different entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate associations or relationships between entities or concepts

    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
    matched
    -0.80
    xtap
    -0.77
     partName
    -0.73
    anke
    -0.72
    mouth
    -0.66
    >[
    -0.66
    BN
    -0.65
    NPR
    -0.65
    soon
    -0.65
    æ©Ł
    -0.64
    POSITIVE LOGITS
     regards
    0.85
     extinction
    0.72
    stood
    0.69
    emonic
    0.68
     Helsinki
    0.68
     excellence
    0.67
    rium
    0.66
     Renaissance
    0.66
     owning
    0.65
    minist
    0.64
    Activations Density 0.072%

    No Known Activations