© 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. 10-RES-JB
    11. 10694
    Prev
    Next
    INDEX
    Explanations

    personal anecdotes and memories

    oai_token-act-pair · gpt-3.5-turbo

    references to personal memories or experiences from childhood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ###
    -0.80
    Auth
    -0.78
    Update
    -0.78
    yip
    -0.73
     intends
    -0.73
    ERG
    -0.72
    xit
    -0.71
     Profit
    -0.71
    Leaks
    -0.71
     confir
    -0.70
    POSITIVE LOGITS
     classmates
    1.28
     summers
    1.24
     babys
    1.13
     preschool
    1.08
     Dad
    1.07
     classmate
    1.05
     taught
    1.03
     puberty
    1.03
     my
    0.99
    Dad
    0.97
    Activations Density 0.559%

    No Known Activations