© 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. 11425
    Prev
    Next
    INDEX
    Explanations

    Turkish words related to various professions and actions, such as 'teacher', 'engineer', and 'driver'

    oai_token-act-pair · gpt-3.5-turbo

    components of the electrical engineering field or related technical 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
    CLASSIFIED
    -0.81
    Mouse
    -0.78
    Hamilton
    -0.75
    Commerce
    -0.72
    Buyable
    -0.71
     Opportunity
    -0.69
    Arcade
    -0.68
     Wilmington
    -0.66
    KNOWN
    -0.65
     Deadpool
    -0.65
    POSITIVE LOGITS
    ku
    1.09
    ı
    1.09
     Ä
    1.02
    vati
    1.01
    nda
    1.01
    kt
    0.99
    fu
    0.99
     ni
    0.98
    ei
    0.97
    È
    0.96
    Activations Density 0.142%

    No Known Activations