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. 16821
    Prev
    Next
    INDEX
    Explanations

    periods of time

    oai_token-act-pair · gpt-3.5-turbo

    temporal prepositions and expressions indicating time periods

    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
    airy
    -0.78
    aeus
    -0.76
     skelet
    -0.72
    tek
    -0.71
    arious
    -0.70
    avorite
    -0.68
    inant
    -0.68
     coord
    -0.64
    Prev
    -0.64
    asha
    -0.64
    POSITIVE LOGITS
     RTX
    0.70
     midnight
    0.64
     refresh
    0.63
    quartered
    0.63
    ober
    0.63
    ument
    0.62
     Palo
    0.60
     curfew
    0.58
     Carolina
    0.58
    asted
    0.58
    Activations Density 0.110%

    No Known Activations