© 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. 7757
    Prev
    Next
    INDEX
    Explanations

    words related to actions or events that involve decision-making or resolution, such as condemning, confirming, representing, explaining, sending, attending, confronting, inviting, inhabiting, preventing, treating, entertaining, inquiring, predicting, destroying, delivering, teaching, protecting, avoiding

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to political and social dynamics

    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
     crane
    -0.63
    ItemTracker
    -0.62
     Strike
    -0.62
     Provision
    -0.61
     Reserve
    -0.60
     brow
    -0.60
     Hurricanes
    -0.57
     sequest
    -0.57
     Hans
    -0.56
     deliberations
    -0.55
    POSITIVE LOGITS
    able
    1.67
    ings
    1.55
    ables
    1.55
    ments
    1.49
    ability
    1.48
    ances
    1.44
    ational
    1.36
    orship
    1.34
    ance
    1.31
    ible
    1.27
    Activations Density 0.257%

    No Known Activations