© 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. 17486
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions of individuals, including actions with moral implications

    oai_token-act-pair · gpt-3.5-turbo

    instances of social or political manipulation and control

    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
    actionDate
    -0.85
    were
    -0.78
    Were
    -0.77
    ERE
    -0.72
     Were
    -0.71
     Matter
    -0.69
     weren
    -0.69
    DragonMagazine
    -0.66
    oubted
    -0.65
     outnumbered
    -0.64
    POSITIVE LOGITS
     prepares
    1.73
     learns
    1.71
     destroys
    1.71
     shuts
    1.70
     recovers
    1.68
     loses
    1.67
     performs
    1.67
     develops
    1.67
     tries
    1.66
     delivers
    1.66
    Activations Density 0.817%

    No Known Activations