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. 3-RES-JB
    6. 19556
    Prev
    Next
    INDEX
    Explanations

    the word "eve" in the context of events or occurrences happening on the night before

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "eve" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ondo
    -0.69
    BuyableInstoreAndOnline
    -0.65
     charism
    -0.65
    opted
    -0.64
    Rated
    -0.62
     Fired
    -0.62
    umbo
    -0.62
    ector
    -0.61
    IED
    -0.60
    ected
    -0.60
    POSITIVE LOGITS
     eve
    1.18
    rette
    0.97
    cape
    0.87
     Eve
    0.84
    uary
    0.83
    ï¸
    0.79
    ¬¼
    0.78
    lyn
    0.76
    eve
    0.73
     Evening
    0.68
    Activations Density 0.004%

    No Known Activations