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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 20480
    Prev
    Next
    INDEX
    Explanations

    references to the brand "Soylent."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific product, particularly "Soy."

    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
    DCS
    -0.70
    Downloadha
    -0.66
    iscopal
    -0.66
     sight
    -0.65
     disenfranch
    -0.65
     CPC
    -0.64
     Hurricanes
    -0.63
    ASED
    -0.62
    utory
    -0.62
     haunt
    -0.62
    POSITIVE LOGITS
     Soy
    1.20
    bean
    1.13
    beans
    1.06
    lio
    0.98
    lings
    0.93
    tank
    0.84
    bits
    0.84
    inka
    0.83
    tis
    0.81
    akov
    0.81
    Activations Density 0.007%

    No Known Activations