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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 6-RES-JB
    6. 3379
    Prev
    Next
    INDEX
    Explanations

    words related to professions and fields of expertise

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various professional and social groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiName
    -0.84
    rontal
    -0.80
     Jericho
    -0.70
     Shutterstock
    -0.68
     molten
    -0.67
     TAMADRA
    -0.66
     unpop
    -0.66
    ï¸
    -0.65
     Shattered
    -0.64
     Lethal
    -0.61
    POSITIVE LOGITS
     alike
    1.32
    workers
    0.80
     enthusiast
    0.79
    icult
    0.73
     administrators
    0.71
    worker
    0.71
     contractors
    0.70
     experts
    0.69
    affiliated
    0.69
    conserv
    0.69
    Activations Density 0.430%

    No Known Activations