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. 18747
    Prev
    Next
    INDEX
    Explanations

    moments or events that are significant or memorable

    oai_token-act-pair · gpt-3.5-turbo

    references to significant or impactful moments

    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
    ä¸Ĭ
    -0.81
    GH
    -0.73
    ply
    -0.70
    PAR
    -0.68
    ãģĮ
    -0.67
    ãĤ´
    -0.66
    cipl
    -0.66
    Steel
    -0.65
    emale
    -0.65
    bard
    -0.65
    POSITIVE LOGITS
    ary
    1.18
    aneously
    1.11
    aries
    1.06
    ous
    1.04
    ously
    0.88
     Moment
    0.85
     moment
    0.85
     moments
    0.84
     gratification
    0.84
    icity
    0.83
    Activations Density 0.024%

    No Known Activations