© 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. 8-RES-JB
    11. 10111
    Prev
    Next
    INDEX
    Explanations

    words related to release dates and platforms for video games and entertainment media

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the release of video games, specifically mentioning regions and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tal
    -0.74
    tre
    -0.71
    ibur
    -0.69
     ingred
    -0.66
     contag
    -0.64
     lodged
    -0.63
    ALSE
    -0.63
    bol
    -0.63
    FORE
    -0.61
    ité
    -0.61
    POSITIVE LOGITS
     conjunction
    1.36
     theaters
    1.18
     lieu
    1.16
     accordance
    1.12
     tandem
    1.08
    clusions
    1.08
     addition
    1.05
    clus
    1.00
     order
    0.99
     partnership
    0.96
    Activations Density 0.302%

    No Known Activations