© 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. 0-RES-JB
    11. 13854
    Prev
    Next
    INDEX
    Explanations

    words related to assurance or certainty

    oai_token-act-pair · gpt-3.5-turbo

    the term "guaranteed" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ald
    -0.74
    iets
    -0.72
    edia
    -0.68
    acter
    -0.67
    encies
    -0.66
    inks
    -0.66
    aign
    -0.64
    iddle
    -0.63
    hof
    -0.63
     Loud
    -0.63
    POSITIVE LOGITS
     guaranteed
    3.77
     guarantees
    2.45
     guarantee
    2.40
     guaranteeing
    2.14
     Guarant
    2.09
     guarant
    1.64
     assured
    1.60
     ensured
    1.42
     insured
    1.26
     secured
    1.15
    Activations Density 0.013%

    No Known Activations