© 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. 9073
    Prev
    Next
    INDEX
    Explanations

    phrases related to discharge, release, or removal

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of discharge or being discharged

    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
    apa
    -0.81
    */(
    -0.73
     Beir
    -0.71
    aque
    -0.67
    ellen
    -0.67
    MSN
    -0.66
    Ear
    -0.66
    chn
    -0.65
     Mond
    -0.65
    xxxx
    -0.64
    POSITIVE LOGITS
     discharge
    1.25
    ysis
    0.98
     discharged
    0.95
    owship
    0.87
    uations
    0.86
    inois
    0.84
    ertation
    0.83
    luent
    0.78
    LECT
    0.76
    ploy
    0.75
    Activations Density 0.010%

    No Known Activations