© 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. 10-RES-JB
    11. 3120
    Prev
    Next
    INDEX
    Explanations

    term "Whatever" followed by a potential action or outcome

    oai_token-act-pair · gpt-3.5-turbo

    the word "whatever" and its variants, indicating a focus on indifference or lack of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iard
    -0.81
    arest
    -0.78
    arie
    -0.76
    auri
    -0.76
    olkien
    -0.75
    ea
    -0.73
    isse
    -0.72
    arb
    -0.71
    aters
    -0.71
    arah
    -0.70
    POSITIVE LOGITS
     else
    1.27
     happens
    1.25
     floats
    1.21
     happened
    1.07
    soever
    0.99
     transpired
    0.87
     arises
    0.87
     comes
    0.79
     emerges
    0.77
     occurs
    0.76
    Activations Density 0.033%

    No Known Activations