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. 12518
    Prev
    Next
    INDEX
    Explanations

    terms related to Indian Pale Ales (IPAs) in the context of beer and brewing

    oai_token-act-pair · gpt-3.5-turbo

    types of beer, particularly IPAs and ales

    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
     Telecommunications
    -0.82
    aido
    -0.81
     Neuroscience
    -0.76
    bilt
    -0.73
     Telecom
    -0.73
    MpServer
    -0.70
    aldo
    -0.69
    operated
    -0.69
    MRI
    -0.68
    romy
    -0.67
    POSITIVE LOGITS
     brewed
    1.30
     flavored
    0.96
     brewing
    0.89
     brewer
    0.88
     conco
    0.88
     brew
    0.84
     flavour
    0.84
     tasting
    0.84
     IPA
    0.83
     poppy
    0.82
    Activations Density 0.020%

    No Known Activations