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. 10-RES-JB
    6. 23897
    Prev
    Next
    INDEX
    Explanations

    calls to action, specifically urging immediate action

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing urgency and immediacy in actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yesterday
    -0.65
     patched
    -0.63
     tomorrow
    -0.61
    ythm
    -0.60
    yp
    -0.58
     nowadays
    -0.57
    zos
    -0.57
    hap
    -0.56
     tonight
    -0.55
     hereafter
    -0.55
    POSITIVE LOGITS
     srfAttach
    0.75
    ģĸ
    0.70
    OTAL
    0.65
    IJ
    0.64
    IDER
    0.64
    reshold
    0.63
    Cola
    0.63
    ECK
    0.63
    EStreamFrame
    0.63
    ħĭ
    0.63
    Activations Density 0.034%

    No Known Activations