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. 17307
    Prev
    Next
    INDEX
    Explanations

    religious and spiritual references

    oai_token-act-pair · gpt-3.5-turbo

    references to significant religious figures or moments

    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
     robotic
    -0.78
     Derby
    -0.76
     robots
    -0.75
     clicks
    -0.74
     offshore
    -0.72
    crew
    -0.71
     subcontract
    -0.70
     stunts
    -0.69
     stunt
    -0.69
     bots
    -0.68
    POSITIVE LOGITS
     Allaah
    1.23
    á¸
    1.18
     Apostle
    1.09
    á¹
    1.08
     Ibn
    1.05
    aimon
    1.02
     scripture
    1.00
    arij
    1.00
     Scripture
    0.99
     Quran
    0.99
    Activations Density 0.165%

    No Known Activations