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. 2885
    Prev
    Next
    INDEX
    Explanations

    mentions of beverages

    oai_token-act-pair · gpt-3.5-turbo

    references to beverages

    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
    ural
    -0.86
    doms
    -0.78
    ures
    -0.75
    uve
    -0.73
    heed
    -0.70
    herty
    -0.68
    ebus
    -0.68
    cephal
    -0.66
    ure
    -0.65
    roe
    -0.65
    POSITIVE LOGITS
     beverage
    1.06
     beverages
    1.05
     drinks
    0.98
     drinkers
    0.97
    gary
    0.97
     cups
    0.93
     brewed
    0.89
     drink
    0.88
    cohol
    0.86
     Sprite
    0.85
    Activations Density 0.026%

    No Known Activations