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. 14250
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wherever"

    oai_token-act-pair · gpt-3.5-turbo

    various forms of the word "where."

    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
    PHOTOS
    -0.66
     Riy
    -0.64
    eers
    -0.64
    Tex
    -0.61
     Lob
    -0.61
    ises
    -0.60
     cape
    -0.60
    oscope
    -0.60
    ãĥ¼ãĤ¯
    -0.60
    ki
    -0.59
    POSITIVE LOGITS
    theless
    0.91
    entimes
    0.91
    terday
    0.90
    nown
    0.89
    leep
    0.84
    selves
    0.83
    phalt
    0.79
    merce
    0.79
    soever
    0.78
     happ
    0.78
    Activations Density 0.070%

    No Known Activations