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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 10573
    Prev
    Next
    INDEX
    Explanations

    the mention of different levels in a video game or program

    oai_token-act-pair · gpt-3.5-turbo

    mentions of game or system levels

    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
    adan
    -0.74
     republic
    -0.73
    atalie
    -0.72
     empires
    -0.70
     monarchy
    -0.69
     republican
    -0.68
    nam
    -0.68
     fortunes
    -0.66
    erry
    -0.66
    rene
    -0.65
    POSITIVE LOGITS
     Level
    3.70
    Level
    2.61
     Levels
    2.16
     LEVEL
    2.12
     level
    1.75
    level
    1.66
    levels
    1.47
     lvl
    1.40
     Tier
    1.38
     Stage
    1.38
    Activations Density 0.020%

    No Known Activations