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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6372
    Prev
    Next
    INDEX
    Explanations

    words related to receiving blessings or being fortunate

    oai_token-act-pair · gpt-3.5-turbo

    expressions of being blessed or gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.76
    ACTION
    -0.75
    RFC
    -0.69
    WAR
    -0.69
    IP
    -0.67
    argument
    -0.64
    */(
    -0.64
     Ogre
    -0.63
     Klu
    -0.63
     AMA
    -0.62
    POSITIVE LOGITS
    ly
    1.01
    ness
    0.95
    oise
    0.95
    liness
    0.93
    frey
    0.93
     blessed
    0.88
    nesses
    0.86
     Bless
    0.84
    eous
    0.83
     bless
    0.81
    Activations Density 0.024%

    No Known Activations