© 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. 11-RES-JB
    11. 6496
    Prev
    Next
    INDEX
    Explanations

    references to memories or things related to memory

    oai_token-act-pair · gpt-3.5-turbo

    references to memory and memory-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ļ½
    -0.74
    wered
    -0.73
    OPLE
    -0.72
    verages
    -0.67
     Harmon
    -0.67
    ats
    -0.65
    eton
    -0.64
    irin
    -0.63
    ounty
    -0.63
    hatt
    -0.62
    POSITIVE LOGITS
     lapse
    0.97
     retrieval
    0.97
     consolidation
    0.85
    fulness
    0.81
    cards
    0.81
    cells
    0.79
     recollection
    0.77
     erased
    0.76
     chips
    0.76
    abilia
    0.74
    Activations Density 0.041%

    No Known Activations