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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23522
    Prev
    Next
    INDEX
    Explanations

    words related to military operations and defense

    oai_token-act-pair · gpt-3.5-turbo

    references to "AD" as it relates to various contexts, likely indicating mentions of advertisements or attention-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
     Clause
    -0.70
     shale
    -0.67
     pandemonium
    -0.66
     Strip
    -0.66
     chlor
    -0.63
     scr
    -0.62
     stopp
    -0.62
     tentacles
    -0.62
     hydra
    -0.62
     stitching
    -0.61
    POSITIVE LOGITS
    AD
    4.10
    ADS
    2.69
    ADE
    2.11
    ads
    1.92
    ad
    1.91
    ADA
    1.88
     AD
    1.81
    ADD
    1.78
    ader
    1.46
    BD
    1.41
    Activations Density 0.009%

    No Known Activations