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. 7-RES-JB
    6. 13040
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to time and urgency

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "just in" followed by various contexts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olor
    -0.77
    impl
    -0.74
    ascript
    -0.71
    pora
    -0.70
    anchester
    -0.64
     devise
    -0.63
    meet
    -0.62
     invari
    -0.60
    etheus
    -0.59
    imar
    -0.59
    POSITIVE LOGITS
    cause
    0.70
    IFIED
    0.66
    ifiable
    0.65
    åŃIJ
    0.64
     luck
    0.62
    soDeliveryDate
    0.62
    OTHER
    0.61
    ï¸
    0.61
    ification
    0.59
     whiff
    0.58
    Activations Density 0.112%

    No Known Activations