© 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
    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. 13690
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Denny" with different levels of activation, possibly indicating a specific focus on a particular entity or concept related to "Denny"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Denny" or variations of it

    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
     behav
    -0.82
    juven
    -0.75
    itud
    -0.73
    spring
    -0.72
    ioch
    -0.70
    pmwiki
    -0.70
     challeng
    -0.69
     plur
    -0.64
     surv
    -0.63
     disclaim
    -0.63
    POSITIVE LOGITS
    enny
    0.98
    oshenko
    0.84
     Penny
    0.80
     Arcade
    0.75
    gdala
    0.72
    ption
    0.70
    ollar
    0.70
    hao
    0.69
    bles
    0.68
    hyde
    0.68
    Activations Density 0.004%

    No Known Activations