Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23934
    Prev
    Next
    INDEX
    Explanations

    the word "Wait" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Wait."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤº
    -0.79
    ighter
    -0.70
    audi
    -0.68
    reb
    -0.68
    insula
    -0.68
    uded
    -0.67
    jac
    -0.66
     Instr
    -0.66
    phrine
    -0.64
    ighters
    -0.63
    POSITIVE LOGITS
    wait
    0.93
     Wait
    0.90
     wait
    0.82
     patiently
    0.80
    ruciating
    0.79
    eful
    0.73
    Wait
    0.72
    resses
    0.72
    pid
    0.70
     Waiting
    0.70
    Activations Density 0.017%

    No Known Activations