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. 16104
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to "ister" or "sarin canister"

    oai_token-act-pair · gpt-3.5-turbo

    the term "minister" 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
     automation
    -0.66
     trending
    -0.63
     earnings
    -0.59
     termination
    -0.58
     Google
    -0.57
     town
    -0.57
     algorithms
    -0.56
     gear
    -0.56
     valuation
    -0.56
     optimization
    -0.56
    POSITIVE LOGITS
    ister
    4.83
    isters
    3.86
    ISTER
    2.85
    istered
    1.86
    istry
    1.39
    iblings
    1.30
    ibling
    1.14
    istor
    1.09
    isting
    1.04
    isted
    1.03
    Activations Density 0.019%

    No Known Activations