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. 8-RES-JB
    6. 5962
    Prev
    Next
    INDEX
    Explanations

    mentions of veils

    oai_token-act-pair · gpt-3.5-turbo

    references to vegetarianism and veganism

    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
     Sparrow
    -0.71
     fracturing
    -0.69
     stripping
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
     writ
    -0.63
    selves
    -0.62
     petitions
    -0.62
    iewicz
    -0.61
     servicing
    -0.61
    manship
    -0.61
    POSITIVE LOGITS
    ggie
    1.45
    gging
    1.27
    ices
    1.16
    gged
    1.15
    ggies
    1.14
    mber
    1.12
    gas
    1.10
    lez
    1.10
    gans
    1.06
    gan
    1.00
    Activations Density 0.030%

    No Known Activations