© 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. 0-RES-JB
    11. 13790
    Prev
    Next
    INDEX
    Explanations

    terms related to the heart and emotions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "heart" and its variations

    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
    ules
    -0.69
     Buk
    -0.67
     deposit
    -0.66
     displaced
    -0.65
     distributed
    -0.61
     Pes
    -0.61
     TODAY
    -0.59
    iability
    -0.58
     described
    -0.57
     subdivision
    -0.56
    POSITIVE LOGITS
    heart
    4.38
    Heart
    2.14
     Heart
    1.71
     heart
    1.61
    hearted
    1.41
    concert
    1.33
     hearts
    1.29
    joy
    1.19
     Hearts
    1.18
    mouth
    1.17
    Activations Density 0.025%

    No Known Activations