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. 8-RES-JB
    6. 19449
    Prev
    Next
    INDEX
    Explanations

    email-related phrases or references

    oai_token-act-pair · gpt-3.5-turbo

    the letter 'e' in various contexts within text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anthem
    -0.70
     Kitchen
    -0.70
     NEC
    -0.67
     Operator
    -0.62
     Katz
    -0.61
     Kats
    -0.61
     Petty
    -0.60
    ãĤ¤ãĥĪ
    -0.60
     Vulkan
    -0.59
     Burton
    -0.59
    POSITIVE LOGITS
    tymology
    1.38
    gypt
    1.27
    agles
    1.24
    ighth
    1.22
    arthed
    1.22
    ternally
    1.21
    ugen
    1.15
    thereum
    1.12
    lements
    1.07
    pee
    1.03
    Activations Density 0.038%

    No Known Activations