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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10124
    Prev
    Next
    INDEX
    Explanations

    verbs with a positive connotation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to actions or situations involving a significant amount or degree of something

    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
    artifacts
    -0.88
    things
    -0.76
    igne
    -0.74
    encies
    -0.74
    :{
    -0.72
    evidence
    -0.72
    archives
    -0.71
    aza
    -0.71
    tests
    -0.69
    lio
    -0.68
    POSITIVE LOGITS
     vengeance
    1.45
     bang
    1.32
     twist
    1.12
     flourish
    1.10
     penchant
    1.00
     flick
    1.00
     smile
    0.99
     wink
    0.98
     caveat
    0.98
     view
    0.98
    Activations Density 0.145%

    No Known Activations