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. 19014
    Prev
    Next
    INDEX
    Explanations

    words related to tension and stress in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases that convey a sense of tension or strained 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
    ocated
    -0.76
    adr
    -0.73
    outed
    -0.70
    STDOUT
    -0.70
    cart
    -0.68
    artney
    -0.68
     redistributed
    -0.68
    cano
    -0.67
    mine
    -0.66
    isle
    -0.66
    POSITIVE LOGITS
     tense
    0.92
    ness
    0.86
     tension
    0.86
    ly
    0.80
     Situation
    0.79
     standoff
    0.78
    lock
    0.75
    ty
    0.71
     suspense
    0.69
     Grip
    0.69
    Activations Density 0.025%

    No Known Activations