© 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. 17251
    Prev
    Next
    INDEX
    Explanations

    phrases related to memories and remnants of the past

    oai_token-act-pair · gpt-3.5-turbo

    references to relics and remnants of the past

    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
    女
    -0.85
    pport
    -0.75
    mpeg
    -0.75
    reon
    -0.73
    raq
    -0.73
    motion
    -0.71
    oto
    -0.69
    wise
    -0.66
    queue
    -0.66
    tarians
    -0.65
    POSITIVE LOGITS
     memories
    1.12
     childhood
    1.06
     Childhood
    0.95
     antiquity
    0.93
    gone
    0.92
     Memories
    0.91
     centuries
    0.87
     past
    0.86
     deceased
    0.86
     traumatic
    0.84
    Activations Density 0.309%

    No Known Activations