© 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. 10-RES-JB
    11. 12267
    Prev
    Next
    INDEX
    Explanations

    specific terms related to computer programming and technology, particularly focusing on instruction, technical elements, and equipment

    oai_token-act-pair · gpt-3.5-turbo

    key concepts related to computer files and security

    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
    ifest
    -0.79
    LGBT
    -0.78
    soType
    -0.78
    Season
    -0.77
    wy
    -0.73
     Herrera
    -0.72
    etsy
    -0.71
     Pride
    -0.70
     ðŁij
    -0.69
     lashes
    -0.67
    POSITIVE LOGITS
     computers
    2.03
     computing
    1.83
     computer
    1.77
     Comput
    1.70
    computer
    1.64
     computational
    1.62
     IBM
    1.62
    puters
    1.61
    Computer
    1.60
     software
    1.57
    Activations Density 0.622%

    No Known Activations