© 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. 2-RES-JB
    11. 10399
    Prev
    Next
    INDEX
    Explanations

    the name 'Mavi'

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Ravi" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    banks
    -0.73
    runner
    -0.72
    bos
    -0.71
    paced
    -0.68
    ween
    -0.68
     wheelchair
    -0.68
    master
    -0.68
    fully
    -0.66
    egg
    -0.66
    telling
    -0.66
    POSITIVE LOGITS
    Äį
    1.13
    Å¡
    0.97
    Äĩ
    0.92
    avi
    0.91
    irus
    0.85
    PLIC
    0.82
     Mehran
    0.82
    ota
    0.81
    adoes
    0.81
    opsis
    0.81
    Activations Density 0.005%

    No Known Activations