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. 5242
    Prev
    Next
    INDEX
    Explanations

    instances of traveling or moving from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and directional phrases related to movement or travel

    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
    Ö¼
    -0.78
    anooga
    -0.76
    iqueness
    -0.72
    Ü
    -0.71
    zsche
    -0.63
    ription
    -0.63
    Angelo
    -0.62
    iety
    -0.62
     pse
    -0.62
    ractor
    -0.62
    POSITIVE LOGITS
     airplanes
    0.94
     submarines
    0.85
     continents
    0.80
    agos
    0.78
    atri
    0.77
     aircraft
    0.73
     cruise
    0.72
     fumes
    0.71
     airplane
    0.71
     Guam
    0.70
    Activations Density 0.248%

    No Known Activations