© 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. 6-RES-JB
    11. 11961
    Prev
    Next
    INDEX
    Explanations

    proper nouns of geographical locations or countries

    oai_token-act-pair · gpt-3.5-turbo

    names of specific places and countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ender
    -0.70
    Constructed
    -0.65
    ãĥ¯ãĥ³
    -0.64
     rendition
    -0.63
    printed
    -0.63
    GREEN
    -0.63
    FORMATION
    -0.63
    Pir
    -0.62
    mit
    -0.61
     yarn
    -0.61
    POSITIVE LOGITS
    atives
    0.92
    zon
    0.90
    tin
    0.88
    osi
    0.85
    ators
    0.84
    ator
    0.82
    ate
    0.82
    va
    0.80
    ately
    0.79
    zsche
    0.78
    Activations Density 0.052%

    No Known Activations