© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 13879
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Samsung"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Samsung" and represents overall document metadata or markers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.81
    ãĥĥãĥĪ
    -0.80
    orget
    -0.76
    umbn
    -0.72
    asure
    -0.71
    avez
    -0.71
    wild
    -0.68
    ghan
    -0.68
    hani
    -0.67
    ebin
    -0.67
    POSITIVE LOGITS
     Electronics
    1.20
     Galaxy
    0.98
    Samsung
    0.86
    ites
    0.80
    itic
    0.77
     Samsung
    0.76
    creen
    0.75
    bee
    0.73
     960
    0.73
    SQL
    0.73
    Activations Density 0.010%

    No Known Activations