© 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. 8-RES-JB
    11. 18630
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotional states, particularly those related to the heart such as warmth, communication, and breaking

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to emotional experiences and sentiments, particularly those invoking the concept of "heart."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sigma
    -0.72
     Motorsport
    -0.66
     unauthorized
    -0.65
     Zup
    -0.63
     newsp
    -0.62
    dq
    -0.62
    aution
    -0.60
     Yugoslav
    -0.59
     elig
    -0.59
     CSI
    -0.59
    POSITIVE LOGITS
    warming
    1.27
    strings
    1.26
    rend
    1.13
    broken
    1.12
    felt
    1.09
    beat
    1.07
    burn
    1.05
    break
    0.93
    worm
    0.93
    bow
    0.93
    Activations Density 0.038%

    No Known Activations