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

    Neuronpedia

    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. 4-RES-JB
    11. 10482
    Prev
    Next
    INDEX
    Explanations

    references to a specific brand or product related to modern technology or entertainment

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Modern" in various contexts

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

    No Comments

    Negative Logits
    avering
    -0.84
    cific
    -0.82
    inventoryQuantity
    -0.74
    aukee
    -0.73
    cial
    -0.73
    vana
    -0.72
    REDACTED
    -0.70
    RAY
    -0.67
    --------------------------------------------------------
    -0.66
    GV
    -0.66
    POSITIVE LOGITS
     Warfare
    1.02
    ization
    0.92
    izations
    0.82
    isation
    0.79
    itized
    0.77
    odon
    0.76
    ists
    0.76
    strate
    0.74
    itary
    0.74
     Modern
    0.74
    Activations Density 0.008%

    No Known Activations