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. 5-RES-JB
    6. 3285
    Prev
    Next
    INDEX
    Explanations

    information related to event details, such as time, location, and schedule

    oai_token-act-pair · gpt-3.5-turbo

    event details such as time, location, and seating information

    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
     brute
    -0.88
     infall
    -0.82
     handwriting
    -0.79
     analysed
    -0.79
     learnt
    -0.78
     botched
    -0.76
     inept
    -0.75
     flawed
    -0.74
     inheritance
    -0.73
     inherited
    -0.73
    POSITIVE LOGITS
    Tickets
    1.11
     TBA
    1.05
     Directions
    0.97
     Doors
    0.96
     Admission
    0.93
    Fest
    0.91
     Starts
    0.90
     TBD
    0.90
     Tickets
    0.87
     Asheville
    0.87
    Activations Density 0.520%

    No Known Activations