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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 4857
    Prev
    Next
    INDEX
    Explanations

    words related to the specific term "Minster"

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Min" and its variations, likely indicating a focus on locations or organizations associated with this term

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wagen
    -0.75
    Reviewer
    -0.74
    VL
    -0.71
    ________________
    -0.68
    arted
    -0.67
    ablo
    -0.64
    isphere
    -0.63
    IVER
    -0.63
    antically
    -0.63
    ament
    -0.63
    POSITIVE LOGITS
     Min
    3.69
    Min
    2.42
     MIN
    1.98
     min
    1.95
    min
    1.92
    MIN
    1.64
     Mini
    1.39
     Minotaur
    1.36
     Minion
    1.31
     Miner
    1.21
    Activations Density 0.012%

    No Known Activations