Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8-RES-JB
    6. 22150
    Prev
    Next
    INDEX
    Explanations

    titles of books or works

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "by" followed by an author or creator's name in titles or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itto
    -0.74
    ptive
    -0.72
    igrate
    -0.71
    cffffcc
    -0.70
    actly
    -0.70
    ptions
    -0.69
    inea
    -0.69
    illance
    -0.69
    bia
    -0.68
    bian
    -0.68
    POSITIVE LOGITS
     virtue
    1.10
    akuya
    0.89
     Joseph
    0.85
     Jorge
    0.84
    products
    0.84
     Keith
    0.84
     Nathaniel
    0.83
     Jonathan
    0.83
     Jeffrey
    0.83
     Gregory
    0.83
    Activations Density 0.092%

    No Known Activations