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. 2-RES-JB
    6. 16871
    Prev
    Next
    INDEX
    Explanations

    words related to ribs or rib-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "ribs" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sunny
    -0.79
     GOODMAN
    -0.78
     SOS
    -0.74
     Coastal
    -0.72
    CHO
    -0.70
     Ceres
    -0.69
     Suc
    -0.69
    eanor
    -0.69
    idad
    -0.67
     Claus
    -0.64
    POSITIVE LOGITS
    bons
    1.35
     rib
    1.07
    bed
    1.01
     Rib
    0.97
    bing
    0.93
     ribs
    0.92
    bent
    0.90
    bon
    0.90
    bones
    0.90
    bit
    0.87
    Activations Density 0.005%

    No Known Activations