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. 9395
    Prev
    Next
    INDEX
    Explanations

    words related to enterprise and production environments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to production and enterprise software

    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
    arium
    -0.93
    terness
    -0.81
    attr
    -0.78
    leon
    -0.77
    illo
    -0.77
    arius
    -0.76
    ativity
    -0.74
    ideshow
    -0.73
     Adin
    -0.73
    hod
    -0.73
    POSITIVE LOGITS
     counterparts
    0.99
     versions
    0.91
     equivalents
    0.85
     counterpart
    0.82
     ones
    0.80
     versus
    0.78
     mode
    0.75
     audiences
    0.75
     editions
    0.75
     realms
    0.75
    Activations Density 0.274%

    No Known Activations