© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12794
    Prev
    Next
    INDEX
    Explanations

    words related to things that are unexpected or surprising

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "surprising."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -1.06
    xia
    -0.91
    nan
    -0.90
    tein
    -0.85
    haps
    -0.84
    iche
    -0.80
    ript
    -0.75
    adian
    -0.75
    claimer
    -0.74
    nery
    -0.73
    POSITIVE LOGITS
     Squid
    0.90
    aneously
    0.87
     surprising
    0.85
    LY
    0.83
     surprises
    0.82
     surpr
    0.79
     enough
    0.79
     coincidence
    0.78
     revelations
    0.77
    Berry
    0.77
    Activations Density 0.015%

    No Known Activations