© 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. 1-RES-JB
    11. 14529
    Prev
    Next
    INDEX
    Explanations

    the word "whatever"

    oai_token-act-pair · gpt-3.5-turbo

    the word "whatever" in various contexts

    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
    enburg
    -0.81
    por
    -0.80
    enberg
    -0.79
    iv
    -0.77
    stra
    -0.76
    eds
    -0.75
     Range
    -0.72
    lee
    -0.71
    ids
    -0.71
    et
    -0.70
    POSITIVE LOGITS
    soever
    1.23
    wcsstore
    1.03
     else
    1.02
     whatever
    0.90
    whatever
    0.90
     toget
    0.88
     happ
    0.83
     transpired
    0.82
     floats
    0.81
     happened
    0.78
    Activations Density 0.009%

    No Known Activations