© 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. 3-RES-JB
    11. 13139
    Prev
    Next
    INDEX
    Explanations

    the word "sentiment"

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotion or opinion

    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
     Mamm
    -0.74
    ctic
    -0.73
    ARDS
    -0.73
    arters
    -0.70
    ummies
    -0.69
    AMS
    -0.68
    DERR
    -0.67
    ÄŁ
    -0.65
    abb
    -0.65
     Journals
    -0.64
    POSITIVE LOGITS
     sentiments
    1.14
     sentiment
    1.07
    ality
    1.01
     guiActiveUn
    0.89
    naire
    0.79
    uated
    0.75
     expressed
    0.74
    igue
    0.74
    ally
    0.73
    TextColor
    0.72
    Activations Density 0.011%

    No Known Activations