Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 2391
    Prev
    Next
    INDEX
    Explanations

    mentions of classic video game consoles

    oai_token-act-pair · gpt-3.5-turbo

    references to vintage gaming systems and emulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thening
    -0.72
    icit
    -0.68
    entin
    -0.68
    hire
    -0.67
    lies
    -0.64
    lier
    -0.63
    ortium
    -0.63
    inances
    -0.63
    irming
    -0.62
    irmation
    -0.62
    POSITIVE LOGITS
     2600
    0.88
     Atari
    0.88
     emulator
    0.86
     Classic
    0.78
     Classics
    0.77
    DOS
    0.76
     Replay
    0.76
     tapes
    0.76
     EDITION
    0.75
     Disk
    0.74
    Activations Density 0.059%

    No Known Activations