© 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. 7-RES-JB
    11. 8498
    Prev
    Next
    INDEX
    Explanations

    keywords related to strong emotional attachment or affection

    oai_token-act-pair · gpt-3.5-turbo

    the term "beloved" and its variants, indicating affection or deep admiration for someone or something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IDER
    -0.81
    anwhile
    -0.76
    agnetic
    -0.75
    idation
    -0.74
    annis
    -0.74
    asse
    -0.73
    ramid
    -0.72
    ettlement
    -0.72
    err
    -0.72
    okin
    -0.71
    POSITIVE LOGITS
     pets
    0.86
     beloved
    0.81
     cherished
    0.77
     childhood
    0.73
     dearly
    0.72
     saint
    0.68
     Creatures
    0.67
     Ones
    0.67
     darling
    0.66
     Idol
    0.66
    Activations Density 0.038%

    No Known Activations