© 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. 8-RES-JB
    11. 3240
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with 'Whether'

    oai_token-act-pair · gpt-3.5-turbo

    the word "whether" and its variations, indicating uncertainty or choices being presented

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agement
    -0.77
    ulations
    -0.72
    thal
    -0.70
    assi
    -0.69
    atari
    -0.68
    bage
    -0.67
    aging
    -0.67
    vention
    -0.66
    ode
    -0.66
    uers
    -0.64
    POSITIVE LOGITS
    soever
    1.09
     consciously
    0.96
     intentional
    0.78
    theless
    0.75
     intentionally
    0.72
     orally
    0.66
     warranted
    0.66
     overtly
    0.65
     includ
    0.64
     trolling
    0.63
    Activations Density 0.028%

    No Known Activations