© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 8053
    Prev
    Next
    INDEX
    Explanations

    phrases related to the distribution of resources or goods

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of distribution, particularly related to resources and wealth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    --+
    -0.70
    gery
    -0.68
     ABE
    -0.68
    glers
    -0.66
    gged
    -0.66
    chest
    -0.65
    ton
    -0.64
     Huss
    -0.63
    astical
    -0.63
    uberty
    -0.61
    POSITIVE LOGITS
     ledger
    0.93
     distribution
    0.92
    ally
    0.92
     distribute
    0.89
     Distribution
    0.87
    al
    0.83
     distributions
    0.82
     distributing
    0.80
    女
    0.78
     leaflets
    0.78
    Activations Density 0.053%

    No Known Activations