© 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. 9-RES-JB
    11. 15426
    Prev
    Next
    INDEX
    Explanations

    mentions of major entities or categories within written works

    oai_token-act-pair · gpt-3.5-turbo

    references to significant organizations or institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    illation
    -0.79
    ordon
    -0.70
    bles
    -0.70
    cise
    -0.69
    diagn
    -0.68
     Reincarn
    -0.68
    amera
    -0.68
    qi
    -0.68
    elf
    -0.68
    enko
    -0.67
    POSITIVE LOGITS
     institutions
    1.39
     brands
    1.37
     corporations
    1.36
     universities
    1.32
     companies
    1.31
     organisations
    1.26
     organizations
    1.26
     firms
    1.26
     industries
    1.24
     retailers
    1.21
    Activations Density 0.211%

    No Known Activations