© 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. 6617
    Prev
    Next
    INDEX
    Explanations

    references to percentages of various quantities in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to electricity generation and consumption

    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
    ĪĴ
    -0.82
    æĦ
    -0.72
    odox
    -0.64
    actionDate
    -0.64
    dating
    -0.62
     gentleman
    -0.61
     Counsel
    -0.60
    ModLoader
    -0.60
    ADRA
    -0.60
     newcom
    -0.59
    POSITIVE LOGITS
     total
    1.22
     population
    1.06
     footprint
    1.00
     GDP
    0.96
     surveyed
    0.96
     workforce
    0.94
    gross
    0.90
    total
    0.89
     worldwide
    0.88
    Total
    0.86
    Activations Density 0.220%

    No Known Activations