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. 18441
    Prev
    Next
    INDEX
    Explanations

    phrases indicating similarity or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote comparisons and similarities

    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
     squash
    -0.77
     bang
    -0.69
     Beng
    -0.64
     Dota
    -0.62
     Bund
    -0.61
    ELY
    -0.59
     demolition
    -0.59
     neighbourhood
    -0.58
     Rumble
    -0.58
     Derby
    -0.57
    POSITIVE LOGITS
    chart
    0.86
    accompan
    0.84
    æ©Ł
    0.82
    ctr
    0.78
    wise
    0.77
    quartered
    0.76
    wcs
    0.72
    forward
    0.70
    initions
    0.70
    nown
    0.70
    Activations Density 0.026%

    No Known Activations