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. 11-RES-JB
    6. 18284
    Prev
    Next
    INDEX
    Explanations

    phrases related to being under investigation or construction

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "under" in various contexts related to scrutiny or investigation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VIDEOS
    -0.79
    aturday
    -0.63
    aries
    -0.60
    ades
    -0.60
    Hello
    -0.59
     unlucky
    -0.59
     supra
    -0.58
     Behind
    -0.58
     Begins
    -0.57
     Ahead
    -0.56
    POSITIVE LOGITS
    written
    1.34
    developed
    1.20
    lain
    1.20
    whelming
    1.20
    util
    1.18
    valued
    1.18
    represented
    1.14
    lined
    1.12
    performing
    1.09
    funded
    1.09
    Activations Density 0.033%

    No Known Activations