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. 4-RES-JB
    6. 3921
    Prev
    Next
    INDEX
    Explanations

    numerical references to liquid measurements, particularly in terms of gallons

    oai_token-act-pair · gpt-3.5-turbo

    quantities of liquid measurement, particularly gallons

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

    No Comments

    Negative Logits
     skelet
    -0.81
    eering
    -0.77
    eer
    -0.74
    spons
    -0.70
     Fram
    -0.67
     sugg
    -0.66
    gotten
    -0.65
    ĻĤ
    -0.64
     rationale
    -0.63
     Krish
    -0.62
    POSITIVE LOGITS
     gallons
    1.18
     litres
    1.15
     barrels
    0.94
     gallon
    0.92
     bottles
    0.89
     spilled
    0.86
     containers
    0.86
     jug
    0.80
    wagen
    0.79
     lbs
    0.77
    Activations Density 0.019%

    No Known Activations