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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11023
    Prev
    Next
    INDEX
    Explanations

    words related to alcoholic spirits

    oai_token-act-pair · gpt-3.5-turbo

    references to spirits in various contexts, especially alcoholic beverages and supernatural entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Brad
    -0.74
    bery
    -0.72
     Bradford
    -0.71
     Bradley
    -0.71
     Citation
    -0.70
    feld
    -0.70
     Bench
    -0.70
     CVE
    -0.69
    =>
    -0.68
    ensor
    -0.66
    POSITIVE LOGITS
     spirits
    4.22
     Spirits
    2.69
     spirit
    2.11
     souls
    1.65
     ghosts
    1.61
    spir
    1.60
    spirit
    1.44
     whis
    1.25
    Spirit
    1.24
     Spirit
    1.22
    Activations Density 0.004%

    No Known Activations