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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 8-RES-JB
    6. 19940
    Prev
    Next
    INDEX
    Explanations

    dates and events that mark an occasion or milestone

    oai_token-act-pair · gpt-3.5-turbo

    events and milestones denoted by the word "mark."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.78
    queue
    -0.72
     polled
    -0.69
     alone
    -0.68
    matter
    -0.66
    soever
    -0.66
     fined
    -0.65
     consulted
    -0.65
     flowed
    -0.64
     quer
    -0.63
    POSITIVE LOGITS
     departure
    1.06
     culmination
    1.00
     anniversary
    1.00
     arrival
    0.99
     milestone
    0.95
     pinnacle
    0.94
     convergence
    0.85
     demise
    0.80
    ieth
    0.80
     rebirth
    0.79
    Activations Density 0.126%

    No Known Activations