© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 11885
    Prev
    Next
    INDEX
    Explanations

    words related to significant events or outcomes, such as victory, success, salvation, and doom

    oai_token-act-pair · gpt-3.5-turbo

    themes related to endings, failures, and survival challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pert
    -0.64
     background
    -0.64
     obser
    -0.60
     advoc
    -0.60
     bulletin
    -0.60
     subt
    -0.58
     inactive
    -0.57
     Instr
    -0.57
    BuyableInstoreAndOnline
    -0.56
    Sample
    -0.55
    POSITIVE LOGITS
     someday
    0.94
    enment
    0.91
    !.
    0.78
    thood
    0.78
     awaits
    0.76
    .
    0.76
    ezvous
    0.76
    *.
    0.75
     sooner
    0.74
    livion
    0.73
    Activations Density 0.691%

    No Known Activations