© 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. 18688
    Prev
    Next
    INDEX
    Explanations

    phrases relating to waiting or anticipation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to decision-making and outcomes

    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
     suspensions
    -0.72
     inconsist
    -0.69
    iencies
    -0.69
    ornings
    -0.66
    esters
    -0.65
    ivism
    -0.64
    pmwiki
    -0.64
    UFF
    -0.62
    oos
    -0.62
    juries
    -0.61
    POSITIVE LOGITS
     winner
    0.91
     imminent
    0.87
     worthy
    0.87
     rightful
    0.86
     desired
    0.85
     duly
    0.85
     favourable
    0.84
     prize
    0.84
     fulfil
    0.83
     suitable
    0.83
    Activations Density 1.073%

    No Known Activations