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. 5130
    Prev
    Next
    INDEX
    Explanations

    Biblical references and verses

    oai_token-act-pair · gpt-3.5-turbo

    references to the Bible

    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
    nesota
    -0.94
    ickr
    -0.79
    ority
    -0.77
     Flavoring
    -0.71
    "]=>
    -0.70
    llular
    -0.69
    ourning
    -0.68
    ivation
    -0.67
    govtrack
    -0.66
    */(
    -0.65
    POSITIVE LOGITS
     scriptures
    0.88
     prophecy
    0.82
     tracts
    0.80
     Bible
    0.79
    ñ
    0.78
     transl
    0.77
     manuscripts
    0.77
     Scriptures
    0.77
     translator
    0.77
     patriarch
    0.76
    Activations Density 0.014%

    No Known Activations