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. 6291
    Prev
    Next
    INDEX
    Explanations

    phrases related to different types of trees, especially the word "Pine."

    oai_token-act-pair · gpt-3.5-turbo

    references to "pine" in various contexts, including trees, cones, and food

    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
    ioch
    -0.73
    enance
    -0.73
    Interstitial
    -0.72
    HCR
    -0.69
    hered
    -0.67
    Money
    -0.67
    =""
    -0.66
    DERR
    -0.66
    ########
    -0.65
    ivation
    -0.65
    POSITIVE LOGITS
    apple
    1.27
    cone
    1.17
    phrine
    1.01
     cones
    0.95
    stal
    0.89
    lla
    0.89
     pine
    0.88
     cone
    0.87
    berry
    0.82
    ll
    0.79
    Activations Density 0.026%

    No Known Activations