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. 9-RES-JB
    6. 15020
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Spanish word "uno" which means "one"

    oai_token-act-pair · gpt-3.5-turbo

    the Spanish word "un," indicating a focus on indefinite articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olls
    -0.77
    OSH
    -0.70
     decaying
    -0.65
    testing
    -0.64
    wolves
    -0.64
    arty
    -0.62
    growing
    -0.62
     Chapman
    -0.62
    tested
    -0.61
    OPLE
    -0.60
    POSITIVE LOGITS
    idad
    0.93
    itud
    0.83
     nu
    0.76
    ici
    0.75
     mund
    0.75
    icit
    0.74
    itas
    0.74
     conflic
    0.73
    oso
    0.73
    ita
    0.72
    Activations Density 0.029%

    No Known Activations