© 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. 18684
    Prev
    Next
    INDEX
    Explanations

    Proper nouns related to people or places

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals, political groups, or specific entities

    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
    izons
    -0.77
    ¥µ
    -0.77
    multiple
    -0.70
    ãĤ¦
    -0.70
    izoph
    -0.68
    atorium
    -0.67
    MpServer
    -0.66
    sample
    -0.66
    etheless
    -0.62
    ļéĨĴ
    -0.62
    POSITIVE LOGITS
     fault
    1.22
     who
    0.94
     versus
    0.93
     alone
    0.90
     deciding
    0.88
     vs
    0.86
     doing
    0.83
     Fault
    0.81
     messing
    0.77
     whom
    0.77
    Activations Density 0.252%

    No Known Activations