© 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. 2-RES-JB
    11. 492
    Prev
    Next
    INDEX
    Explanations

    words related to 'Valentine'

    oai_token-act-pair · gpt-4-turbo

    references to the word "Valentine"

    oai_token-act-pair · gpt-3.5-turbo

    references to the holiday of Valentine's Day

    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
    ulhu
    -1.03
    alach
    -0.88
    lopp
    -0.86
    ollow
    -0.79
    orough
    -0.79
    progress
    -0.75
    OLOG
    -0.72
    raltar
    -0.71
    wered
    -0.71
    ackle
    -0.71
    POSITIVE LOGITS
     Valentine
    1.21
     mosqu
    0.94
     Valent
    0.89
     Staples
    0.83
    gang
    0.75
     Sprite
    0.73
     Claus
    0.71
     ann
    0.66
     Slug
    0.66
     Jarrett
    0.64
    Activations Density 0.005%

    No Known Activations