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. 14874
    Prev
    Next
    INDEX
    Explanations

    references to the location "Dunedin."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Dun."

    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
    OHN
    -0.78
    NRS
    -0.71
    xual
    -0.65
    âĸĪâĸĪ
    -0.64
    Magikarp
    -0.63
    INT
    -0.61
    >>>>>>>>
    -0.61
    ONS
    -0.61
    shapeshifter
    -0.60
     Pyro
    -0.59
    POSITIVE LOGITS
    edin
    1.03
    wich
    1.01
    querque
    1.00
    leys
    0.94
    lap
    0.92
    igan
    0.89
    ogh
    0.89
    iet
    0.87
    agon
    0.85
    omial
    0.85
    Activations Density 0.013%

    No Known Activations