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. 7-RES-JB
    6. 15619
    Prev
    Next
    INDEX
    Explanations

    people, groups, or ideas being supported or backed by others

    oai_token-act-pair · gpt-3.5-turbo

    references to proposals and endorsements

    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
    --+
    -0.71
    lance
    -0.67
     pandemonium
    -0.67
     Nig
    -0.66
    igated
    -0.65
    dust
    -0.65
    ivan
    -0.65
    licted
    -0.64
    fect
    -0.64
     Affect
    -0.62
    POSITIVE LOGITS
     initiatives
    0.88
     legalization
    0.83
     proposition
    0.82
     ideals
    0.81
     efforts
    0.80
     uncond
    0.78
     endeavors
    0.78
     independence
    0.77
     candidacy
    0.75
     idea
    0.72
    Activations Density 0.512%

    No Known Activations