© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20145
    Prev
    Next
    INDEX
    Explanations

    words related to going beyond or transcending

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Beyond" and related concepts

    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
    è¦ļéĨĴ
    -0.71
    abet
    -0.68
    chens
    -0.67
    oping
    -0.65
    KEY
    -0.65
    upp
    -0.65
    aceous
    -0.64
    owell
    -0.64
    otle
    -0.64
    alian
    -0.64
    POSITIVE LOGITS
     Beyond
    0.96
    Beyond
    0.88
     Wond
    0.83
     Worlds
    0.79
     Horizons
    0.75
    Outside
    0.71
    esis
    0.71
    ĸļ
    0.70
    smanship
    0.70
    lehem
    0.68
    Activations Density 0.008%

    No Known Activations