© 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. 5230
    Prev
    Next
    INDEX
    Explanations

    words related to a sense of transcendence or going beyond normal limits

    oai_token-act-pair · gpt-3.5-turbo

    the word "Beyond" and its usage in various contexts

    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
     pairs
    -0.64
     randomly
    -0.64
     receivers
    -0.62
    isc
    -0.62
     correction
    -0.62
    zzle
    -0.62
    pson
    -0.62
    oult
    -0.61
     type
    -0.61
     complain
    -0.60
    POSITIVE LOGITS
     Beyond
    3.62
    Beyond
    2.55
     Behind
    1.48
     beyond
    1.44
     Above
    1.42
     Bene
    1.36
    yond
    1.35
     Below
    1.24
     Into
    1.22
     Outside
    1.22
    Activations Density 0.012%

    No Known Activations