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. 12934
    Prev
    Next
    INDEX
    Explanations

    references to craft beer or craft brewing

    oai_token-act-pair · gpt-3.5-turbo

    references to craft beverages, particularly craft beer

    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
     Fas
    -0.93
     NCT
    -0.86
     Mum
    -0.78
     Tut
    -0.74
     Mub
    -0.72
     GOODMAN
    -0.72
     Canaver
    -0.71
    phia
    -0.71
     Burk
    -0.69
     Mubarak
    -0.66
    POSITIVE LOGITS
    smanship
    2.23
    spe
    1.23
    manship
    1.05
    ivism
    0.93
    shape
    0.86
    hest
    0.85
    fruit
    0.85
    craft
    0.84
     crafts
    0.84
    friend
    0.84
    Activations Density 0.022%

    No Known Activations