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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10307
    Prev
    Next
    INDEX
    Explanations

    phrases related to software, gaming, and specific interests or hobbies

    oai_token-act-pair · gpt-3.5-turbo

    phrases that engage the reader with direct address and conditions

    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
    izable
    -0.71
    burgh
    -0.70
    ises
    -0.68
    izations
    -0.67
    egu
    -0.66
    pedia
    -0.64
    EVA
    -0.64
    negie
    -0.64
    "},
    -0.63
    ancial
    -0.62
    POSITIVE LOGITS
     wondering
    1.32
     interested
    1.31
     lucky
    1.25
     unsure
    1.23
     unlucky
    1.20
     willing
    1.14
     unfamiliar
    1.10
     fortunate
    1.10
     tempted
    1.07
     planning
    1.05
    Activations Density 0.111%

    No Known Activations