© 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. 11-RES-JB
    11. 23928
    Prev
    Next
    INDEX
    Explanations

    descriptions related to the absence of artificial additives and ingredients in products

    oai_token-act-pair · gpt-3.5-turbo

    words associated with natural and chemical-free products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.69
    inently
    -0.65
    liam
    -0.63
    itled
    -0.61
    eele
    -0.56
    LIST
    -0.56
    ready
    -0.55
    terday
    -0.55
    stown
    -0.54
    uers
    -0.54
    POSITIVE LOGITS
     whatsoever
    1.79
     nor
    1.45
    nor
    1.05
     or
    1.03
     anymore
    0.98
     either
    0.95
     lest
    0.88
     (<
    0.82
     beforehand
    0.81
     except
    0.79
    Activations Density 0.388%

    No Known Activations