© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 6602
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations in Spanish-speaking countries, particularly Guatemala

    oai_token-act-pair · gpt-3.5-turbo

    the French article "la" and related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    worth
    -0.82
    Austin
    -0.73
    Allen
    -0.71
    âĦ¢:
    -0.70
    locks
    -0.70
    Sharp
    -0.70
    icky
    -0.69
    sworth
    -0.68
    Alien
    -0.66
    acks
    -0.66
    POSITIVE LOGITS
     ré
    0.89
     Univers
    0.85
     lang
    0.85
     dé
    0.81
     lett
    0.80
     histor
    0.80
     civilisation
    0.79
     mosqu
    0.77
     fem
    0.75
     cart
    0.75
    Activations Density 0.025%

    No Known Activations