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. 15675
    Prev
    Next
    INDEX
    Explanations

    commands or prompts requesting the enabling of JavaScript or disabling of ad blockers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "enable" and related phrases about enabling features or support

    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
    schild
    -0.70
    oled
    -0.68
    ļé
    -0.68
    doms
    -0.66
    dk
    -0.65
    DERR
    -0.64
     Gibbs
    -0.64
    quartered
    -0.63
    Ö¼
    -0.62
    arah
    -0.62
    POSITIVE LOGITS
    taboola
    0.82
     Javascript
    0.81
    Java
    0.79
     yourselves
    0.75
    Emb
    0.74
     Tayyip
    0.73
    utions
    0.70
     spoiler
    0.69
     Scroll
    0.68
    ":[
    0.67
    Activations Density 0.021%

    No Known Activations