Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 17824
    Prev
    Next
    INDEX
    Explanations

    phrases related to genuinely positive or sincere expressions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of sincerity or genuineness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ean
    -0.79
     belts
    -0.72
     Dominion
    -0.70
     Seven
    -0.68
    erto
    -0.67
    ackle
    -0.67
    anish
    -0.65
     Destination
    -0.65
     Spray
    -0.64
    ammy
    -0.63
    POSITIVE LOGITS
    uine
    0.85
     sincere
    0.81
     genuinely
    0.80
     apologise
    0.74
    DonaldTrump
    0.73
     genuine
    0.71
     sincerely
    0.71
     unres
    0.68
     remorse
    0.68
    olkien
    0.68
    Activations Density 0.002%

    No Known Activations