© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 20128
    Prev
    Next
    INDEX
    Explanations

    references to specific quantities of liquid measured in gallons

    oai_token-act-pair · gpt-3.5-turbo

    references to measurements of liquid volume

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -0.77
     Fram
    -0.72
    western
    -0.70
    hood
    -0.66
    eer
    -0.65
    arya
    -0.65
    developed
    -0.64
     Crunch
    -0.63
    eve
    -0.62
     promise
    -0.62
    POSITIVE LOGITS
     gallons
    1.30
     litres
    1.09
     gallon
    1.04
     jug
    0.89
    soDeliveryDate
    0.84
    wagen
    0.83
     barrels
    0.83
     closet
    0.80
    renheit
    0.80
     horsepower
    0.74
    Activations Density 0.007%

    No Known Activations