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. 14182
    Prev
    Next
    INDEX
    Explanations

    words related to transportation infrastructure, specifically roads and vehicles

    oai_token-act-pair · gpt-3.5-turbo

    words related to transportation and vehicles

    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
     Nur
    -0.70
    imov
    -0.68
     STATS
    -0.67
     Milan
    -0.63
     1947
    -0.63
     Maharashtra
    -0.60
    ãĤ¢
    -0.60
     1931
    -0.59
     1943
    -0.59
     Proposition
    -0.58
    POSITIVE LOGITS
    culosis
    1.00
    oshenko
    0.91
    ulhu
    0.85
    nel
    0.81
    umatic
    0.80
    obl
    0.78
    _>
    0.77
    emouth
    0.75
    hiba
    0.74
    ilight
    0.73
    Activations Density 0.074%

    No Known Activations