© 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. 2-RES-JB
    11. 14019
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities or unfortunate events

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "fortune" and related concepts of opportunity

    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
    ients
    -0.76
    kson
    -0.75
    oses
    -0.70
    geries
    -0.70
    ors
    -0.69
    ossal
    -0.68
    ascade
    -0.67
    paio
    -0.66
    enegger
    -0.66
    istry
    -0.66
    POSITIVE LOGITS
     consolation
    0.86
    nown
    0.79
    llor
    0.76
    ortun
    0.72
    strument
    0.71
    ties
    0.71
    lla
    0.71
    FTWARE
    0.67
    STEM
    0.67
     Bucc
    0.65
    Activations Density 0.024%

    No Known Activations