Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4470
    Prev
    Next
    INDEX
    Explanations

    locations within Dublin

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Dublin and its associated entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ļéĨĴ
    -0.73
    oted
    -0.72
    olars
    -0.71
    aturdays
    -0.71
    kaya
    -0.70
    imov
    -0.69
    anooga
    -0.68
    alus
    -0.68
     autop
    -0.68
    ļé
    -0.67
    POSITIVE LOGITS
     Gael
    0.91
     Duffy
    0.83
     Cork
    0.76
     Byrne
    0.75
     McCann
    0.74
    patrick
    0.73
     Ireland
    0.72
    forth
    0.72
    mares
    0.72
    Ireland
    0.70
    Activations Density 0.087%

    No Known Activations