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

    Neuronpedia

    Jacobian LensNEW
    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. 13296
    Prev
    Next
    INDEX
    Explanations

    references to randomness or things described as random

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "random" and related concepts

    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
    ibia
    -0.82
    uay
    -0.80
    acht
    -0.77
    vana
    -0.71
     advocate
    -0.70
    bia
    -0.69
    Aid
    -0.67
    cia
    -0.67
    ume
    -0.67
    makers
    -0.67
    POSITIVE LOGITS
     random
    3.69
    random
    2.89
    Random
    2.53
     randomly
    2.52
     Random
    2.45
     randomized
    2.01
     arbitrary
    1.35
     RAND
    1.20
     rand
    1.19
     entropy
    1.17
    Activations Density 0.014%

    No Known Activations