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. 4749
    Prev
    Next
    INDEX
    Explanations

    references to the technology company Samsung

    oai_token-act-pair · gpt-3.5-turbo

    references to the Samsung brand and its products

    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
    ablishment
    -0.79
    ãĥĥãĥĪ
    -0.78
    ebin
    -0.73
    lying
    -0.72
    orget
    -0.71
    umbn
    -0.71
    wild
    -0.70
    naires
    -0.69
    asure
    -0.68
    Ñĭ
    -0.68
    POSITIVE LOGITS
    Samsung
    1.16
     Electronics
    1.12
     Galaxy
    1.07
     Samsung
    1.03
    amsung
    0.96
    creen
    0.88
    awei
    0.84
    itic
    0.77
    SQL
    0.76
    ITE
    0.74
    Activations Density 0.009%

    No Known Activations