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. 2-RES-JB
    6. 24454
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to mobile applications and app stores, with a high emphasis on the term "App."

    oai_token-act-pair · gpt-3.5-turbo

    references to the App Store

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    terday
    -1.05
    Ń·
    -0.78
     formal
    -0.69
    κ
    -0.68
     caucus
    -0.68
     Karl
    -0.68
    warts
    -0.66
    qqa
    -0.65
    EngineDebug
    -0.63
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    POSITIVE LOGITS
    ointment
    1.29
    reciation
    1.21
    alach
    1.18
    earances
    1.08
    rentices
    1.08
    rehens
    1.07
    ointed
    1.06
    arent
    1.04
    earance
    1.03
    arel
    1.00
    Activations Density 0.014%

    No Known Activations