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. 9778
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to nuclear reactions

    oai_token-act-pair · gpt-3.5-turbo

    scientific terms related to nuclear physics and research

    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
     symp
    -0.70
     fitting
    -0.60
     psychiat
    -0.59
     timely
    -0.58
    reau
    -0.57
     widest
    -0.57
     trout
    -0.57
    rency
    -0.56
     answ
    -0.56
     skelet
    -0.56
    POSITIVE LOGITS
    aneous
    0.90
    SQL
    0.87
    culosis
    0.86
    âĶĢâĶĢâĶĢâĶĢ
    0.77
    à¼
    0.76
    ogo
    0.70
    È
    0.69
    ution
    0.68
    inous
    0.67
    aneously
    0.66
    Activations Density 0.252%

    No Known Activations