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. 12-RES-JB
    6. 14509
    Prev
    Next
    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udeb
    -0.75
    rollers
    -0.69
    20439
    -0.66
    ARA
    -0.64
    Reviewer
    -0.63
    erous
    -0.63
    uras
    -0.62
    failed
    -0.62
    issue
    -0.61
    earances
    -0.61
    POSITIVE LOGITS
     smack
    1.15
     atop
    0.99
     midway
    0.98
     centrally
    0.96
     adjacent
    0.96
     southwest
    0.95
     northwest
    0.95
     northeast
    0.94
     southeast
    0.94
     halfway
    0.92
    Activations Density 0.099%

    No Known Activations