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. 2751
    Prev
    Next
    INDEX
    Explanations

    references to locations specifically related to parking lots

    oai_token-act-pair · gpt-3.5-turbo

    references to parking lots

    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
    ighth
    -0.76
    emonic
    -0.72
    podcast
    -0.69
    sonian
    -0.69
    iolet
    -0.69
     streng
    -0.66
     homebrew
    -0.66
    alam
    -0.64
     fearless
    -0.62
    ãģĦ
    -0.61
    POSITIVE LOGITS
     entrances
    0.85
    aurus
    0.84
    tyard
    0.84
    pole
    0.81
    area
    0.76
     entrance
    0.74
     doors
    0.73
    stones
    0.73
    tery
    0.71
     stalls
    0.71
    Activations Density 0.021%

    No Known Activations