Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 19520
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences with the word "increasingly"

    oai_token-act-pair · gpt-3.5-turbo

    the word "increasingly" and related patterns indicating a growth or escalation of concerns or issues

    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
    gio
    -0.82
     Polo
    -0.81
    ieu
    -0.77
    boy
    -0.74
     Execution
    -0.69
     Relief
    -0.68
    oops
    -0.67
    ño
    -0.66
     Celeb
    -0.66
     Yard
    -0.66
    POSITIVE LOGITS
     reliant
    0.94
     frustrated
    0.91
     agitated
    0.83
     embold
    0.81
     mathemat
    0.81
    wcs
    0.80
     aroused
    0.78
     accustomed
    0.74
     disruptive
    0.74
     polarized
    0.73
    Activations Density 0.021%

    No Known Activations