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. 1-RES-JB
    6. 17483
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific terms related to political events and locations with the word "Yatra" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to political campaigns or movements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dx
    -0.82
    ģ«
    -0.80
    NER
    -0.73
    Roaming
    -0.73
    paced
    -0.71
    ership
    -0.68
     oats
    -0.68
     accelerator
    -0.68
    Attack
    -0.68
     CLIENT
    -0.67
    POSITIVE LOGITS
    udeau
    0.88
    ught
    0.87
    isance
    0.86
    ppelin
    0.85
    illac
    0.83
    aina
    0.82
    isha
    0.82
    urdue
    0.80
    iller
    0.79
     Lumpur
    0.79
    Activations Density 0.019%

    No Known Activations