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. 1-RES-JB
    6. 4215
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Samsung'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Samsung."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.80
    naires
    -0.78
    ãĥĥãĥĪ
    -0.76
    asure
    -0.73
    umbn
    -0.72
     Hitchcock
    -0.71
    ebin
    -0.70
    lying
    -0.70
    edly
    -0.69
    atre
    -0.67
    POSITIVE LOGITS
    Samsung
    1.32
     Samsung
    1.19
    amsung
    1.17
     Galaxy
    1.09
     Electronics
    1.09
    awei
    1.01
    creen
    0.92
    SQL
    0.82
     phones
    0.78
     Xiaomi
    0.77
    Activations Density 0.007%

    No Known Activations