© 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. 0-RES-JB
    11. 1747
    Prev
    Next
    INDEX
    Explanations

    technical terms or jargon related to transportation and translation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Trans" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renown
    -0.80
     Jaw
    -0.74
    hammer
    -0.71
     grapes
    -0.70
     Avery
    -0.70
     vengeance
    -0.67
     crater
    -0.67
     candy
    -0.66
     fret
    -0.66
     odds
    -0.66
    POSITIVE LOGITS
    Trans
    3.82
    trans
    2.11
     Trans
    1.92
     TRANS
    1.52
    Tele
    1.50
    Translation
    1.47
     TRAN
    1.46
     trans
    1.43
    Transfer
    1.39
    rans
    1.36
    Activations Density 0.012%

    No Known Activations