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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21896
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an increasing level or intensity of something

    oai_token-act-pair · gpt-3.5-turbo

    the word "increasingly" and its usage in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elo
    -0.73
    mates
    -0.71
    gio
    -0.70
    yet
    -0.69
    boy
    -0.69
    fen
    -0.68
    cule
    -0.67
     Release
    -0.67
     Polo
    -0.65
    poke
    -0.64
    POSITIVE LOGITS
     frustrated
    0.97
     reliant
    0.93
     embold
    0.88
     agitated
    0.87
     alarmed
    0.86
     polarized
    0.84
     annoyed
    0.79
     impatient
    0.77
     erratic
    0.77
     aggressive
    0.77
    Activations Density 0.046%

    No Known Activations