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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 1017
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Ir" with high activation values

    oai_token-act-pair · gpt-3.5-turbo

    variations and references to Ireland or Irish entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcs
    -0.79
    artney
    -0.74
    ulhu
    -0.72
    iage
    -0.70
    ecause
    -0.65
     Puzzles
    -0.63
    iversary
    -0.62
     Uncommon
    -0.60
    hement
    -0.60
     ABE
    -0.59
    POSITIVE LOGITS
    ventus
    0.64
    ãĥ¼ãĥ
    0.64
    ftime
    0.63
    itably
    0.59
    nah
    0.58
    vous
    0.58
    udic
    0.57
    roth
    0.57
    åĤ
    0.56
    ¿½
    0.56
    Activations Density 0.147%

    No Known Activations