© 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. 0-RES-JB
    11. 4085
    Prev
    Next
    INDEX
    Explanations

    references to specific quantities of liquid measured in gallons

    oai_token-act-pair · gpt-3.5-turbo

    measurements related to liquid volumes

    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
    rave
    -0.79
    wig
    -0.71
    arya
    -0.68
     Cyber
    -0.65
     Shaw
    -0.64
    stre
    -0.64
    ret
    -0.63
    eve
    -0.63
    Rob
    -0.60
     Tel
    -0.59
    POSITIVE LOGITS
     gallons
    3.49
     gallon
    3.01
     litres
    2.24
    gall
    1.84
     barrels
    1.42
     kWh
    1.31
     buckets
    1.28
     gal
    1.18
     pint
    1.17
     gasoline
    1.15
    Activations Density 0.028%

    No Known Activations