© 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. 11-RES-JB
    11. 9446
    Prev
    Next
    INDEX
    Explanations

    organizations and groups involved in societal or political issues

    oai_token-act-pair · gpt-3.5-turbo

    references to various stakeholders in social or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lasts
    -0.70
     fuse
    -0.69
     shalt
    -0.68
     utilizes
    -0.67
     achieves
    -0.65
     solves
    -0.64
     suffice
    -0.64
     prototype
    -0.63
     behaves
    -0.60
     exhibit
    -0.60
    POSITIVE LOGITS
     worried
    1.14
     alarmed
    1.10
     outraged
    1.07
     concerned
    1.04
     frustrated
    1.01
     wary
    1.01
     who
    1.00
     angered
    0.97
     skeptical
    0.97
     unhappy
    0.96
    Activations Density 0.335%

    No Known Activations