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

    Neuronpedia

    APICircuit 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. 19641
    Prev
    Next
    INDEX
    Explanations

    words related to social gatherings and activities, particularly those involving food and drink like bars, picnics, and BBQs

    oai_token-act-pair · gpt-3.5-turbo

    references to bars or bar environments

    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
     Liang
    -0.70
    IDS
    -0.69
     Voy
    -0.67
     Virus
    -0.67
    OTA
    -0.65
    ils
    -0.64
    ENG
    -0.64
    iev
    -0.63
    ctive
    -0.63
     Exper
    -0.62
    POSITIVE LOGITS
     bar
    3.70
     bars
    2.79
    bar
    2.41
     Bar
    2.30
    bars
    2.13
    Bar
    2.05
     Bars
    2.03
     BAR
    1.73
     bart
    1.60
     bartender
    1.53
    Activations Density 0.015%

    No Known Activations