© 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. 0-RES-JB
    11. 16636
    Prev
    Next
    INDEX
    Explanations

    references to heavy metal music

    oai_token-act-pair · gpt-3.5-turbo

    references to the video game Metal Gear

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scram
    -0.76
     prob
    -0.74
     uncom
    -0.73
     ding
    -0.73
     Jacobs
    -0.70
    iership
    -0.69
     boosters
    -0.68
     deficit
    -0.68
     scholarship
    -0.65
     todd
    -0.65
    POSITIVE LOGITS
     Metal
    3.57
    Metal
    2.77
    metal
    2.14
     Metall
    1.35
    MET
    1.28
     Konami
    1.26
     Guitar
    1.20
     MET
    1.18
     Snake
    1.17
     Plastic
    1.16
    Activations Density 0.027%

    No Known Activations