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. 3717
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to delays

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "delay" and its variations

    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
    ortium
    -0.91
    bold
    -0.81
    tained
    -0.80
    rim
    -0.78
    ramid
    -0.77
    arov
    -0.75
    onym
    -0.70
    kaya
    -0.69
    incerity
    -0.67
    orically
    -0.67
    POSITIVE LOGITS
     gratification
    1.19
     delaying
    0.97
     delays
    0.96
     Delay
    0.94
     delay
    0.93
     cooker
    0.90
     delayed
    0.87
     postp
    0.86
     indefinitely
    0.82
     cancell
    0.76
    Activations Density 0.022%

    No Known Activations