© 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. 9108
    Prev
    Next
    INDEX
    Explanations

    the mention of specific video game companies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of video game companies

    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
     queens
    -0.72
    utherford
    -0.70
     Labrador
    -0.62
     kittens
    -0.62
    Els
    -0.61
     wildfire
    -0.60
    aram
    -0.58
    %%%%
    -0.58
    cyl
    -0.58
    Frameworks
    -0.57
    POSITIVE LOGITS
    isoft
    1.03
    hesda
    1.02
     Enix
    0.96
     Konami
    0.91
     Capcom
    0.86
    idian
    0.85
     Developer
    0.80
     Publisher
    0.79
    Xbox
    0.77
    Nintendo
    0.75
    Activations Density 0.024%

    No Known Activations