© 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. 2938
    Prev
    Next
    INDEX
    Explanations

    significant events or decisions related to political or social issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of significant events or decisions that involve public policy or governance

    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
     undecided
    -0.82
     prosec
    -0.79
     blocker
    -0.77
     ende
    -0.76
     waterfall
    -0.75
     deflation
    -0.75
     mustache
    -0.74
    icho
    -0.74
     beh
    -0.74
     hesitate
    -0.73
    POSITIVE LOGITS
    Interested
    1.75
    According
    1.65
    The
    1.58
    Speaking
    1.47
    Officials
    1.44
    Beginning
    1.43
    Following
    1.43
    Writing
    1.42
    Sources
    1.41
    During
    1.40
    Activations Density 0.232%

    No Known Activations