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. 16181
    Prev
    Next
    INDEX
    Explanations

    specific city names

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character '´' and references to "Yang."

    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
    liest
    -0.86
    perture
    -0.77
    DAQ
    -0.76
     millenn
    -0.72
    iaries
    -0.72
    NRS
    -0.70
    alty
    -0.69
    iciency
    -0.67
    ciating
    -0.66
     Rouhani
    -0.66
    POSITIVE LOGITS
    ãĤ¡
    1.03
    lda
    0.83
    ossus
    0.80
    onel
    0.78
    ogen
    0.76
    ogue
    0.74
    gren
    0.74
    ppo
    0.73
    inx
    0.71
    town
    0.70
    Activations Density 0.031%

    No Known Activations