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. 2-RES-JB
    6. 2378
    Prev
    Next
    INDEX
    Explanations

    Spanish names, particularly those associated with politics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ente" within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tub
    -0.69
    map
    -0.68
    twitter
    -0.67
    matic
    -0.67
    krit
    -0.67
    ODUCT
    -0.66
    wings
    -0.65
    */(
    -0.64
    matically
    -0.64
    HCR
    -0.64
    POSITIVE LOGITS
    ente
    1.29
    uous
    0.90
    zon
    0.88
    terness
    0.88
    uve
    0.86
    ellen
    0.83
     Aires
    0.81
     Marcos
    0.79
    sov
    0.79
    ner
    0.76
    Activations Density 0.009%

    No Known Activations