© 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. 10-RES-JB
    11. 1220
    Prev
    Next
    INDEX
    Explanations

    words related to verifying or confirming information, such as terms like "verify" and phrases like "verify email" or "verify internet authority."

    oai_token-act-pair · gpt-3.5-turbo

    references to company names or financial terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imet
    -0.75
    aily
    -0.71
    ember
    -0.64
    agara
    -0.64
    antically
    -0.62
    emetery
    -0.62
    oppers
    -0.62
    izzle
    -0.59
    ciplinary
    -0.58
    leans
    -0.58
    POSITIVE LOGITS
     MN
    1.54
     LD
    1.50
     KS
    1.47
     TX
    1.46
     NB
    1.45
     DL
    1.45
     CA
    1.44
     FB
    1.44
     NT
    1.43
     DT
    1.42
    Activations Density 0.436%

    No Known Activations