© 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. 11-RES-JB
    11. 1972
    Prev
    Next
    INDEX
    Explanations

    terms related to places, particularly those with a connection to the Spanish language

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations and organizations related to Hispanic culture and civil rights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rods
    -0.69
     worms
    -0.68
     trolling
    -0.67
     Phelps
    -0.67
     eyebrows
    -0.67
     NK
    -0.66
     talents
    -0.65
     Junk
    -0.64
     seekers
    -0.64
     slack
    -0.64
    POSITIVE LOGITS
    idad
    1.20
    ité
    1.17
    ÃŃa
    1.09
    encia
    1.07
    ê
    1.05
    ña
    1.04
    tera
    1.00
    ère
    1.00
    issance
    0.98
    agne
    0.98
    Activations Density 0.115%

    No Known Activations