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. 4-RES-JB
    6. 5049
    Prev
    Next
    INDEX
    Explanations

    references to transportation infrastructure, particularly focusing on roads and their conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to roads and their conditions

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

    No Comments

    Negative Logits
    ividual
    -0.88
    ority
    -0.81
    arians
    -0.75
    illian
    -0.72
     Wong
    -0.70
    iaries
    -0.69
     homegrown
    -0.69
    rators
    -0.67
    arian
    -0.66
    tle
    -0.65
    POSITIVE LOGITS
    ways
    1.17
     roads
    1.05
    blocks
    0.98
     highways
    0.93
     Roads
    0.90
    block
    0.90
    lane
    0.89
     tyres
    0.89
    road
    0.88
     arteries
    0.87
    Activations Density 0.023%

    No Known Activations