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. 5-RES-JB
    6. 8713
    Prev
    Next
    INDEX
    Explanations

    similes comparing actions to physical actions or states

    oai_token-act-pair · gpt-3.5-turbo

    the article "a" used in various contexts

    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
     furthermore
    -0.83
     namely
    -0.80
    videos
    -0.78
    alties
    -0.77
     Adin
    -0.77
    bars
    -0.75
    uses
    -0.75
    hess
    -0.73
    olicy
    -0.73
    Edit
    -0.72
    POSITIVE LOGITS
     bunch
    1.06
     lot
    0.91
     typical
    0.90
     handful
    0.88
     precursor
    0.87
     dozen
    0.85
     normal
    0.84
     placeholder
    0.83
     gateway
    0.82
     combination
    0.81
    Activations Density 0.161%

    No Known Activations