© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11658
    Prev
    Next
    INDEX
    Explanations

    words related to strong positive feelings or preferences towards someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loves" and expressions of affection

    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
     clearance
    -0.68
     prompt
    -0.66
     clear
    -0.64
     preliminary
    -0.64
     additional
    -0.64
     result
    -0.64
     further
    -0.63
     sufficient
    -0.63
    éŃĶ
    -0.61
     trace
    -0.61
    POSITIVE LOGITS
     loves
    3.30
     hates
    2.28
     loved
    1.90
     likes
    1.77
     prefers
    1.65
     cares
    1.63
     enjoys
    1.61
     wants
    1.54
     knows
    1.52
     love
    1.52
    Activations Density 0.013%

    No Known Activations