© 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. 11-RES-JB
    11. 7554
    Prev
    Next
    INDEX
    Explanations

    specific instances of the word "nothing"

    oai_token-act-pair · gpt-3.5-turbo

    the recurring theme of "nothing" or expressions indicating lack or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAFT
    -0.69
    PsyNetMessage
    -0.65
    ippers
    -0.65
     Shutterstock
    -0.63
    essing
    -0.63
    riers
    -0.59
    ardi
    -0.59
    ql
    -0.58
    oise
    -0.58
    YN
    -0.58
    POSITIVE LOGITS
     else
    1.08
     happens
    0.99
     compares
    0.96
     prevents
    0.94
     justifies
    0.94
     beats
    0.93
     happened
    0.93
    Else
    0.91
     lasts
    0.90
     bothers
    0.87
    Activations Density 0.046%

    No Known Activations