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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 9040
    Prev
    Next
    INDEX
    Explanations

    words related to gaming consoles

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming consoles

    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
    itated
    -0.80
    pattern
    -0.75
     Kund
    -0.70
    noon
    -0.69
    lein
    -0.69
    lar
    -0.68
    lights
    -0.68
    wei
    -0.66
    itating
    -0.65
    yon
    -0.65
    POSITIVE LOGITS
     consoles
    0.84
    Ħ¢
    0.80
     console
    0.80
     ports
    0.72
     emulator
    0.69
     Chips
    0.68
    ORPG
    0.67
    izo
    0.66
    AMA
    0.66
    Console
    0.65
    Activations Density 0.017%

    No Known Activations