© 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. 1-RES-JB
    11. 11436
    Prev
    Next
    INDEX
    Explanations

    verbs related to the emission of various types of energy or particles

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with light and radiation emissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anova
    -0.82
    esan
    -0.71
     Arch
    -0.68
     Acqu
    -0.64
     Alban
    -0.63
     Everyday
    -0.62
     Chall
    -0.62
    sic
    -0.61
     Slav
    -0.61
     Revival
    -0.60
    POSITIVE LOGITS
     emit
    1.42
     emits
    1.38
     emitting
    1.37
     emitted
    1.25
     emission
    1.23
     emissions
    0.99
    orescence
    0.85
     emanating
    0.80
     spew
    0.79
    terness
    0.76
    Activations Density 0.008%

    No Known Activations