Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 2154
    Prev
    Next
    INDEX
    Explanations

    the word "random"

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to randomness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ossier
    -0.80
    PRO
    -0.77
    SHARE
    -0.75
    raints
    -0.73
    rex
    -0.73
    IDS
    -0.71
    yer
    -0.71
    ept
    -0.71
    hid
    -0.70
    ippi
    -0.70
    POSITIVE LOGITS
    istically
    1.05
     assortment
    0.96
    aneously
    0.96
     randomly
    0.94
     random
    0.90
    ised
    0.87
    isable
    0.83
    izable
    0.83
    aneous
    0.74
     strangers
    0.73
    Activations Density 0.015%

    No Known Activations