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. 6196
    Prev
    Next
    INDEX
    Explanations

    season-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to specific seasons and seasonal events

    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
    hai
    -0.77
    aware
    -0.69
    enei
    -0.64
    plete
    -0.63
    stract
    -0.62
     Fram
    -0.62
    weak
    -0.61
    mercial
    -0.60
     sten
    -0.60
     downed
    -0.59
    POSITIVE LOGITS
     opener
    0.92
     finale
    0.92
    ally
    0.87
     premiere
    0.82
    ings
    0.77
    ticket
    0.69
    ı
    0.67
     eve
    0.65
    aments
    0.65
    igraph
    0.64
    Activations Density 0.036%

    No Known Activations