© 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. 11-RES-JB
    11. 9897
    Prev
    Next
    INDEX
    Explanations

    file extensions and specific programming terms

    oai_token-act-pair · gpt-3.5-turbo

    programming-related syntax and file types, particularly in scripting and markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inav
    -0.76
    åħī
    -0.67
    necess
    -0.66
    appropriate
    -0.64
    ijah
    -0.64
    ourge
    -0.62
    iannopoulos
    -0.62
    isations
    -0.62
     Democracy
    -0.62
     democracy
    -0.60
    POSITIVE LOGITS
    tml
    1.19
     Mehran
    1.02
    #
    0.94
     file
    0.93
     FILE
    0.88
     =================================================================
    0.81
     @@
    0.81
    ttp
    0.81
     File
    0.78
     âĶľâĶĢâĶĢ
    0.77
    Activations Density 0.066%

    No Known Activations