© 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. 9-RES-JB
    11. 3125
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive feelings towards accomplishments and actions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of pride and achievement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beware
    -0.69
     Concern
    -0.68
     Questions
    -0.62
     Beware
    -0.61
    shock
    -0.60
     Tune
    -0.58
    uish
    -0.57
    Shock
    -0.57
    ikers
    -0.57
    ranged
    -0.56
    POSITIVE LOGITS
     accomplished
    0.94
     wrought
    0.93
     done
    0.84
     transpired
    0.80
     presented
    0.78
     happening
    0.77
     unfold
    0.75
     preached
    0.73
     achieved
    0.71
     manufact
    0.68
    Activations Density 0.200%

    No Known Activations