© 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. 15203
    Prev
    Next
    INDEX
    Explanations

    phrases or names related to the location "Tuzla"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "La," likely indicating references to locations or organizations

    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
    manship
    -0.93
    lessly
    -0.83
    lers
    -0.81
    ELL
    -0.73
    lings
    -0.70
    lication
    -0.69
    worthiness
    -0.68
    policy
    -0.68
    leness
    -0.67
    lich
    -0.67
    POSITIVE LOGITS
    uthor
    1.10
    uder
    1.09
    ibrary
    0.94
    uren
    0.93
    igh
    0.87
    xton
    0.87
    pling
    0.86
    vel
    0.85
    heed
    0.84
    ques
    0.83
    Activations Density 0.022%

    No Known Activations