© 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. 4-RES-JB
    11. 7073
    Prev
    Next
    INDEX
    Explanations

    phrases related to challenging authority or social norms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dare" in various contexts

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

    No Comments

    Negative Logits
    urgy
    -0.80
    effic
    -0.74
    winner
    -0.65
     Rite
    -0.63
    Unity
    -0.60
     Methods
    -0.60
     Means
    -0.60
    iple
    -0.60
    entials
    -0.59
    ulators
    -0.58
    POSITIVE LOGITS
     dare
    1.08
     Dare
    0.95
    ngth
    0.91
     daring
    0.86
     defy
    0.82
     dared
    0.82
     boldly
    0.75
    geon
    0.72
     penetrate
    0.72
     provoke
    0.70
    Activations Density 0.014%

    No Known Activations