© 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. 1-RES-JB
    11. 5437
    Prev
    Next
    INDEX
    Explanations

    references to the company "Square Enix."

    oai_token-act-pair · gpt-3.5-turbo

    references to "Square" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERAL
    -0.81
    è£ħ
    -0.67
    omez
    -0.66
    iesel
    -0.63
    icus
    -0.62
    é»Ĵ
    -0.62
    oan
    -0.62
    essor
    -0.61
    enegger
    -0.61
    ̶
    -0.61
    POSITIVE LOGITS
     Enix
    1.50
     Square
    1.19
    Square
    1.12
     Mile
    0.90
    moil
    0.80
    cade
    0.80
    pants
    0.79
     Feet
    0.76
    plates
    0.75
    square
    0.73
    Activations Density 0.010%

    No Known Activations