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. 3988
    Prev
    Next
    INDEX
    Explanations

    terms related to technology, especially encryption, communication protocols, and internet technologies

    oai_token-act-pair · gpt-3.5-turbo

    references to the internet and its associated technologies

    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
    HAEL
    -0.75
    allah
    -0.74
    terness
    -0.72
    rition
    -0.68
    reath
    -0.66
    okes
    -0.65
    azar
    -0.65
    chu
    -0.64
    ermanent
    -0.63
    icide
    -0.63
    POSITIVE LOGITS
     Internet
    1.44
     internet
    1.41
    Internet
    1.21
     IoT
    1.15
     Web
    1.12
     web
    1.10
     cloud
    1.09
    internet
    1.06
     blockchain
    1.03
     computing
    1.01
    Activations Density 0.293%

    No Known Activations