© 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. 1-RES-JB
    11. 14083
    Prev
    Next
    INDEX
    Explanations

    verbs related to ensuring and guaranteeing

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions about guaranteeing conditions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bid
    -0.78
     Obj
    -0.71
     Nanto
    -0.68
     cents
    -0.67
    Beer
    -0.67
    figure
    -0.65
    fig
    -0.65
    GER
    -0.64
    NetMessage
    -0.63
    âĵĺ
    -0.63
    POSITIVE LOGITS
    ĵĺ
    0.93
     ensuring
    0.91
     compr
    0.88
     conduc
    0.88
     ensure
    0.87
     ensured
    0.87
    rity
    0.87
     Ensure
    0.86
     pestic
    0.85
     ensures
    0.85
    Activations Density 0.016%

    No Known Activations