Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24502
    Prev
    Next
    INDEX
    Explanations

    the name "Les" in various contexts and forms

    oai_token-act-pair · gpt-3.5-turbo

    the term "Schles" or its variations, indicating a focus on a specific person's name throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raviolet
    -0.88
    rador
    -0.78
     Seym
    -0.69
    ĻĤ
    -0.67
     citiz
    -0.66
    yrinth
    -0.65
    tains
    -0.65
    atever
    -0.64
     carbohyd
    -0.63
     affili
    -0.61
    POSITIVE LOGITS
    bians
    1.17
    bian
    1.16
    bury
    1.14
    hip
    1.10
    ques
    1.08
    mith
    1.05
    ttes
    1.02
    creen
    1.01
    burg
    1.01
    ville
    0.99
    Activations Density 0.024%

    No Known Activations