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. 21528
    Prev
    Next
    INDEX
    Explanations

    dates and locations from news articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of slashes or parentheses within the text

    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
     prey
    -0.74
     disgu
    -0.70
     record
    -0.69
     inqu
    -0.69
     records
    -0.67
     predators
    -0.66
     advert
    -0.66
     rug
    -0.66
     accus
    -0.66
     infiltr
    -0.65
    POSITIVE LOGITS
    AFP
    1.09
    Flickr
    1.08
    Courtesy
    1.08
    Getty
    1.07
    Bloomberg
    1.01
    ËĪ
    0.94
    CBC
    0.94
    Staff
    0.90
    jon
    0.90
    via
    0.89
    Activations Density 0.028%

    No Known Activations