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. 3-RES-JB
    6. 10951
    Prev
    Next
    INDEX
    Explanations

    references to transportation vehicles commonly used for commuting

    oai_token-act-pair · gpt-3.5-turbo

    mentions of transportation vehicles, particularly shuttle buses and shuttles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ichita
    -0.76
     confir
    -0.74
    oln
    -0.72
    ures
    -0.70
    uries
    -0.69
     Extrem
    -0.68
    ettings
    -0.68
    ombies
    -0.68
    utenberg
    -0.67
    andi
    -0.65
    POSITIVE LOGITS
     shuttle
    1.08
    bay
    0.81
     Shuttle
    0.79
    pod
    0.79
     ferry
    0.78
     Cruise
    0.75
    WAY
    0.74
     Challenger
    0.74
    lift
    0.74
     buses
    0.72
    Activations Density 0.007%

    No Known Activations