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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 3536
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental bodies or policies

    oai_token-act-pair · gpt-3.5-turbo

    references to natural resources

    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
    iversary
    -0.80
    ĪĴ
    -0.76
    λ
    -0.73
    channelAvailability
    -0.72
    ¯
    -0.70
    ²¾
    -0.70
    arella
    -0.68
     Kaufman
    -0.68
    gdala
    -0.67
    lihood
    -0.67
    POSITIVE LOGITS
     Conservation
    0.83
     supply
    0.81
     holdings
    0.81
    afety
    0.81
     reserves
    0.79
     resources
    0.79
    iculture
    0.76
     futures
    0.73
     superpower
    0.73
     commodities
    0.73
    Activations Density 0.038%

    No Known Activations