Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 2683
    Prev
    Next
    INDEX
    Explanations

    mentions of ingredients, specifically coconut milk and coconut-related products

    oai_token-act-pair · gpt-3.5-turbo

    references to coconut 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
    inges
    -0.79
    IGH
    -0.79
    ettings
    -0.78
    utherford
    -0.76
    earable
    -0.75
    baugh
    -0.74
    IGN
    -0.72
    PsyNetMessage
    -0.71
     seeker
    -0.70
    Drug
    -0.67
    POSITIVE LOGITS
    ensis
    0.88
     resin
    0.85
    hedral
    0.84
     coconut
    0.82
     oil
    0.80
     palm
    0.79
    grave
    0.76
     dioxide
    0.75
     Oil
    0.74
     cream
    0.74
    Activations Density 0.018%

    No Known Activations