© 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. 8-RES-JB
    11. 7620
    Prev
    Next
    INDEX
    Explanations

    phrases related to swallowing or ingestion

    oai_token-act-pair · gpt-3.5-turbo

    actions related to consuming or ingesting substances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ements
    -0.83
    ////////////////
    -0.78
    ////////
    -0.72
    iances
    -0.68
    isphere
    -0.66
    ohn
    -0.66
    iator
    -0.65
    efeated
    -0.65
    say
    -0.64
    croft
    -0.63
    POSITIVE LOGITS
     gum
    0.87
    ipes
    0.84
     swallow
    0.81
    meat
    0.80
    anut
    0.79
     worms
    0.76
     flakes
    0.75
    cake
    0.74
    IBLE
    0.73
    dragon
    0.72
    Activations Density 0.075%

    No Known Activations