© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 23035
    Prev
    Next
    INDEX
    Explanations

    mentions of specific states in the United States

    oai_token-act-pair · gpt-3.5-turbo

    references to state entities and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ®
    -0.72
    ®
    -0.62
    alach
    -0.61
    uggish
    -0.60
    IGHTS
    -0.60
    idious
    -0.59
    âĦ¢
    -0.57
    ®,
    -0.56
    aq
    -0.55
     magically
    -0.55
    POSITIVE LOGITS
    wide
    0.83
     Intermediate
    0.81
    hood
    0.71
    hei
    0.68
     Islanders
    0.68
    Assembly
    0.66
    é¾
    0.66
    quote
    0.66
    stice
    0.64
    ois
    0.62
    Activations Density 0.146%

    No Known Activations