© 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. 3-RES-JB
    11. 1782
    Prev
    Next
    INDEX
    Explanations

    names that include the word "Den" and related words

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific individual or entity named "Den."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    committee
    -0.70
    cffffcc
    -0.69
    raltar
    -0.68
     ABE
    -0.67
    anwhile
    -0.65
    EED
    -0.65
    mph
    -0.65
    mobi
    -0.65
     Typh
    -0.64
    sych
    -0.62
    POSITIVE LOGITS
    izens
    1.15
    omination
    1.10
    omin
    1.07
    izen
    1.04
    zel
    1.01
    itus
    0.92
    heim
    0.89
     Den
    0.89
    ocide
    0.88
    unciation
    0.87
    Activations Density 0.007%

    No Known Activations