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. 24213
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Jordan."

    oai_token-act-pair · gpt-3.5-turbo

    the name "Jordan."

    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
    ntil
    -0.77
    forms
    -0.73
    emetery
    -0.72
    ancial
    -0.71
    ULAR
    -0.71
     nutrit
    -0.71
     redund
    -0.68
    roup
    -0.68
    teenth
    -0.68
    ulum
    -0.67
    POSITIVE LOGITS
     Jordan
    1.10
    Jordan
    0.95
     Peterson
    0.92
    olson
    0.84
    sey
    0.81
     Henderson
    0.80
    oglu
    0.80
    allah
    0.77
    pora
    0.77
    endish
    0.75
    Activations Density 0.012%

    No Known Activations