© 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. 17115
    Prev
    Next
    INDEX
    Explanations

    opportunities or advantageous situations

    oai_token-act-pair · gpt-3.5-turbo

    references to opportunities and grievances

    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
    agos
    -0.71
    atives
    -0.68
    BuyableInstoreAndOnline
    -0.68
     Whitman
    -0.66
    agascar
    -0.65
     Underground
    -0.65
    loo
    -0.64
     notebook
    -0.64
     Caribbean
    -0.64
    aldo
    -0.64
    POSITIVE LOGITS
    ĺħ
    0.98
    ourt
    0.89
     remem
    0.87
    sit
    0.81
    ĵĺ
    0.81
    ressing
    0.79
     pse
    0.79
    ours
    0.77
     congr
    0.74
     opp
    0.74
    Activations Density 0.018%

    No Known Activations