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. 0-RES-JB
    6. 14397
    Prev
    Next
    INDEX
    Explanations

    the string "ust" preceded by a letter, which could potentially be a shorthand for the word "trust" or represent a specific concept or entity

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "bust" and its derivatives

    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
     invitations
    -0.70
     PRO
    -0.64
     bypass
    -0.64
     Mulcair
    -0.63
     associ
    -0.63
     Crusher
    -0.61
     clipboard
    -0.61
     cler
    -0.60
     cleric
    -0.59
    skip
    -0.59
    POSITIVE LOGITS
    ust
    4.52
    UST
    2.29
    ustration
    1.76
    usting
    1.66
    usters
    1.65
    uster
    1.62
    usted
    1.62
    urt
    1.07
    ud
    0.97
    ulk
    0.96
    Activations Density 0.017%

    No Known Activations