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. 19693
    Prev
    Next
    INDEX
    Explanations

    words related to urgent or extreme situations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "desperate" indicating urgent or dire situations

    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
    roma
    -0.82
    rust
    -0.77
    ership
    -0.74
    rats
    -0.73
    icipated
    -0.72
    Ģ
    -0.71
    nesota
    -0.71
    agree
    -0.70
    inion
    -0.70
    ificantly
    -0.69
    POSITIVE LOGITS
     pleas
    0.81
     conflic
    0.75
     plea
    0.75
     desperate
    0.73
     pleading
    0.73
     desperation
    0.72
     situations
    0.72
     Measures
    0.72
     desperately
    0.72
     migrants
    0.69
    Activations Density 0.032%

    No Known Activations