© 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. 2-RES-JB
    11. 17349
    Prev
    Next
    INDEX
    Explanations

    technical terms related to specific software and game development tools

    oai_token-act-pair · gpt-3.5-turbo

    mentions of gaming or software technologies, particularly related to the "Epic" and "Unreal" brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    creen
    -0.88
    ieu
    -0.76
    ³³³³³³³³³³³³³³³³
    -0.74
     Sammy
    -0.73
    ODUCT
    -0.65
    allery
    -0.65
    SPONSORED
    -0.64
     Julio
    -0.63
    eering
    -0.63
    holders
    -0.63
    POSITIVE LOGITS
    ered
    0.92
    urious
    0.91
    ensions
    0.80
    ropy
    0.77
     Fest
    0.74
     Medic
    0.72
    rative
    0.71
    reme
    0.70
    ocratic
    0.69
    ension
    0.69
    Activations Density 0.021%

    No Known Activations