© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 640
    Prev
    Next
    INDEX
    Explanations

    keywords related to visual aspects or aesthetics, particularly focusing on the word "visually"

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of visual aesthetics in films

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éļ
    -0.72
    iped
    -0.72
    Dest
    -0.68
    hap
    -0.68
    jas
    -0.67
     stockpile
    -0.66
    agle
    -0.66
    orters
    -0.65
    orage
    -0.65
    uclear
    -0.65
    POSITIVE LOGITS
     massage
    0.69
    istered
    0.68
     Yoga
    0.68
     enjoyed
    0.66
    utra
    0.66
    ccording
    0.66
     Monk
    0.63
     awaits
    0.60
     meditation
    0.60
    geist
    0.60
    Activations Density 0.000%

    No Known Activations