© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18447
    Prev
    Next
    INDEX
    Explanations

    emotional descriptors relating to the heart and eyes

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating emotional impact or intensity, particularly related to heartwarming and eye-catching experiences

    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
     Suc
    -0.77
     ABE
    -0.70
     Cree
    -0.67
     minors
    -0.66
     payday
    -0.65
    \<
    -0.63
    iatus
    -0.63
     Ceres
    -0.63
    ulhu
    -0.62
     Chains
    -0.61
    POSITIVE LOGITS
    eye
    1.17
    tight
    1.08
    shaped
    1.07
    sized
    1.04
    saving
    1.03
    dead
    1.01
    feel
    0.99
    cross
    0.98
    friendly
    0.98
    brain
    0.95
    Activations Density 0.085%

    No Known Activations