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. 0-RES-JB
    6. 3805
    Prev
    Next
    INDEX
    Explanations

    phrases related to deserving something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a sense of entitlement or rights

    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
     circular
    -0.60
     Red
    -0.54
     stationary
    -0.54
     dissolved
    -0.53
     reading
    -0.53
     peripheral
    -0.53
     Grey
    -0.53
     bal
    -0.52
     red
    -0.51
     Station
    -0.51
    POSITIVE LOGITS
     deserve
    3.88
     deserves
    2.78
     deserved
    2.36
     deserving
    1.87
     owe
    1.53
     belong
    1.37
     qualify
    1.26
     merit
    1.22
     rightfully
    1.22
     worthy
    1.17
    Activations Density 0.009%

    No Known Activations